Codex vs Conductor

Agent access

1. ai-native userPoint an agent at llms.txt or agent-oriented docs

   weight 2 · round to Conductor
   Codex~partialprobed4/10

   A dedicated llms.txt file is absent (404 at platform.openai.com/llms.txt), but Codex does publish machine-readable markdown docs (learn.chatgpt.com/docs/codex/cli.md) confirmed reachable by probe, which is an agent-friendly doc format an AI agent could be pointed at. Missing for 10: a standard llms.txt manifest, evidence of agents actually being pointed at these docs, and confirmation across all doc pages (docs/codex.md also 404s).

   • [probe] “PROBE llms.txt: HTTP 404 at https://platform.openai.com/llms.txt”
   • [probe] “PROBE docs-md: HTTP 404 at https://platform.openai.com/docs/codex.md”
   • [probe] “official CLI documented at https://learn.chatgpt.com/docs/codex/cli”

   proof ↗⚑ flag

   Conductor✓fullprobed9/10

   Direct probe confirms llms.txt is live and served at https://www.conductor.build/llms.txt with agent-oriented summary, plus a full docs.md markdown mirror for agent consumption. missing for 10: no independent/community confirmation that external agents actually consume these files successfully.

   • [probe] “PROBE llms.txt: HTTP 200 at https://www.conductor.build/llms.txt # Conductor > Conductor is a Mac app that lets you run many coding agents …”
   • [probe] “PROBE docs-md: HTTP 200 at https://www.conductor.build/docs.md --- title: "Introduction" url: "/docs" description: "Learn what Conductor is …”

   proof ↗⚑ flag

2. ai-native userRun the product headlessly / in CI for automation

   weight 2 · round to Codex
   Codex✓fullclaimed8/10

   Codex CLI explicitly documents non-interactive execution via `codex exec` for use in repeatable workflows, scripts, and CI/CD pipelines (codex-docs-19, codex-docs-32), and permissions/sandbox controls can be configured for unattended runs (codex-docs-17, codex-docs-39). Missing for 10: no independent case study or CI provider (e.g. GitHub Actions) integration example, and no explicit exit-code/output-format spec for CI parsing.

   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [claimed-docs] “Set the boundaries for each run — /permissions: Choose when Codex can edit files or run commands without asking, and inspect the active sand…”

   proof ↗⚑ flag

   Conductor~partialprobed6/10

   Conductor supports scheduled/CI-like automation via 'routines' that run on a schedule or GitHub Action, plus a programmatic API and hosted MCP server for managing cloud workspaces headlessly, and cloud agents can run builds/tests without confirmation. However, it is fundamentally a Mac GUI app, and there's no evidence of a standalone CLI or true headless binary for arbitrary CI pipelines outside GitHub Actions. missing for 10: dedicated CLI/headless binary for generic CI systems, independent evidence of routines/GitHub Action working reliably in production, clarity on full non-interactive operation outside the Mac app.

   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [probe] “official MCP server documented at https://www.conductor.build/docs/api/mcp”

   proof ↗⚑ flag

3. ai-native userPlug MCP servers into this product so it can use their tools

   weight 3 · round to Codex
   Codex✓fullclaimed9/10

   Codex CLI explicitly supports adding local/remote MCP servers via `codex mcp add`, inspecting available tools before use, and viewing active servers via `/mcp`; this configuration is shared across ChatGPT desktop app, CLI, and IDE extension. Docs also describe using MCP to connect to third-party tools like browsers or Figma. Missing for 10: independent hands-on verification of MCP tool usage in a real session beyond first-party docs.

   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”
   • [claimed-docs] “The ChatGPT desktop app, Codex CLI, and IDE extension share this configuration. Once you configure your MCP servers, you can switch among th…”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation, or t…”
   • [claimed-docs] “codex mcp add <server-name> --env VAR1=VALUE1 --env VAR2=VALUE2 -- <stdio server-command>”
   • [claimed-docs] “In the `codex` TUI, use `/mcp` to see your active MCP servers.”

   proof ↗⚑ flag

   Conductor—none0/10

   Evidence only shows Conductor exposing its OWN hosted MCP server so external MCP clients (ChatGPT, Claude, Codex) can manage Conductor's cloud workspaces (conductor-docs-14, conductor-probe-4) — the reverse direction of what the story asks. There is no documentation or community mention of a user being able to add/configure external MCP servers inside Conductor so its hosted coding agents (Claude Code, Codex, Cursor, OpenCode) can consume their tools.

   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [probe] “official MCP server documented at https://www.conductor.build/docs/api/mcp”

   proof ↗⚑ flag

4. ai-native userConnect an agent via an official MCP server

   weight 3 · round to Conductor
   Codex~partialclaimed5/10

   Codex explicitly supports running itself as an MCP server (codex mcp-server) so other MCP clients can connect, but OpenAI's own docs mark this interface 'experimental' and now 'deprecated', pointing users to a newer 'Codex app server' as the recommended replacement. This is a genuine server-mode capability (not just Codex-as-MCP-client), but the deprecation and lack of independent hands-on confirmation of the replacement's stability keep it from a full verdict. Missing for 10: independent corroboration that the current 'Codex app server' MCP mode works reliably in production, and clearer first-party documentation of its interface now that the original is deprecated.

   • [github] “Codex MCP Server Interface [experimental]: a JSON-RPC API that runs over the Model Context Protocol (MCP) transport to control a local Codex…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”
   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”

   proof ↗⚑ flag

   Conductor✓fullprobed8/10

   Conductor documents a hosted MCP server that lets ChatGPT, Claude, Codex, and other MCP clients manage cloud workspaces, corroborated by a dedicated probe hit confirming the docs page exists. Missing for 10: independent/hands-on community confirmation of actually connecting an external agent via this MCP server (all community evidence discusses other features, not MCP usage).

   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [probe] “official MCP server documented at https://www.conductor.build/docs/api/mcp”

   proof ↗⚑ flag

5. ai-native userUse an official CLI

   weight 2 · round to Codex
   Codex✓fullprobed9/10

   Codex ships an official, well-documented CLI (npm install -g @openai/codex) with rich agentic capabilities: local repo editing, exec/non-interactive scripting, MCP support, subagents, image input, sandbox/permissions control, cloud task delegation, and shell completions — all first-party documented and confirmed via GitHub repo and docs. Missing for 10: independent hands-on benchmarking specifically of CLI workflows (community evidence focuses mostly on model quality/UX rather than CLI mechanics) and some Linux-specific gaps noted by users.

   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [github] “npm install -g @openai/codex”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Split up a larger investigation — subagents: Ask Codex to delegate focused work to specialized agents, then bring their findings back into t…”
   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [claimed-docs] “Install the Codex CLI with the standalone installer for macOS and Linux.”
   • [probe] “official CLI documented at https://learn.chatgpt.com/docs/codex/cli”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor is documented as a Mac GUI app with a programmatic API and hosted MCP server, but no evidence pack item describes an official Conductor CLI tool; the only CLI mention is a user leveraging their own 'local GitHub CLI auth', which is unrelated.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [community] “Fixed! You can now give Conductor fine-grained GitHub repository access. Or, skip the integration and use your local GitHub CLI auth.”

   proof ↗⚑ flag

6. ai-native userDrive the product through a documented public API

   weight 3 · round to Conductor
   Codex~partialcommunity5/10

   Codex documents multiple programmatic entry points — an MCP server interface for JSON-RPC control (though explicitly marked deprecated/experimental in favor of an undocumented 'app server'), a non-interactive `codex exec` mode for scripts/CI, and 'API key' usage — but these come with real caveats: API-key use 'requires additional setup', the flagship gpt-5.3-codex model was reportedly not yet available via API, and the primary MCP server route is deprecated rather than a stable first-class API. missing for 10: a single stable, non-deprecated documented public API surface, confirmation that the current model is API-accessible, and independent corroboration that third parties successfully drive Codex via this API.

   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [github] “Codex MCP Server Interface [experimental]: a JSON-RPC API that runs over the Model Context Protocol (MCP) transport to control a local Codex…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”

   proof ↗⚑ flag

   Conductor✓fullprobed7/10

   Conductor documents a public API for programmatically managing cloud workspaces (create workspaces, send prompts, read agent replies) plus a hosted MCP server for AI clients like ChatGPT/Claude/Codex to drive it. Missing for 10: a published OpenAPI/reference spec (probe found only 404s for schema files) and independent/hands-on developer corroboration of API usage.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [probe] “official MCP server documented at https://www.conductor.build/docs/api/mcp”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.conductor.build/openapi.json, https://www.conductor.build/swagger.json, https://www.cond…”

   proof ↗⚑ flag

7. ai-native userIssue scoped/least-privilege API credentials for an agent

   weight 2 · round to Codex
   Codex~partialclaimed5/10

   OpenAI's platform docs describe RBAC and project/org-scoped API keys/custom roles, and Codex can authenticate via an API key (codex-gh-4), so scoped credentials are technically available to a Codex-using account. However, none of the evidence ties this RBAC/API-key scoping specifically to configuring or restricting a Codex agent's own permissions — missing for 10: Codex-specific docs on issuing least-privilege keys for agent sessions, guidance on scoping credentials per-task/per-repo, and independent confirmation that this RBAC applies to Codex's own execution rather than just general API access.

   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”

   proof ↗⚑ flag

   Conductor~partialcommunity4/10

   Community threads document that Conductor originally required full read/write GitHub access with no fine-grained scoping, which users flagged as risky; the developers later added a GitHub App integration for fine-grained repo access (or use of local GitHub CLI auth) as a fix, showing partial progress toward least-privilege credentials but not a documented, general mechanism for issuing scoped API credentials for agents beyond GitHub repo access. Missing for 10: no documentation of scoped/least-privilege credentials for the Conductor API/MCP server itself, no explicit policy on token scoping for non-GitHub integrations, and no independent verification that the new GitHub App permissions are truly minimal in practice.

   • [community] “Any way to have it not require full write access to your entire GitHub account?”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”
   • [community] “I was really excited to try this but this does NOT work the way I expected. I wanted a simple git worktree manager for my existing, already-…”
   • [community] “Right now the app uses GitHub's OAuth sign in which unfortunately doesn't allow for fine-grained permissions... We're switching our sign-in …”
   • [community] “Fixed! You can now give Conductor fine-grained GitHub repository access. Or, skip the integration and use your local GitHub CLI auth.”
   • [claimed-docs] “Bring your own subscriptions and keys”

   proof ↗⚑ flag

8. ai-native userBuild against official SDKs

   weight 2 · round to Codex
   Codex~partialcommunity6/10

   Codex is a coding agent, but the evidence shows a genuine SDK-adjacent surface: the underlying OpenAI Responses API has an official OpenAPI spec and multi-language code samples (Python, TypeScript, Go, Ruby, Java, HTTP, CLI), and Codex integrates via CLI/MCP for programmatic extension. However, there is no evidence of an official Codex-specific SDK (as opposed to the general OpenAI API SDK), and API access for the Codex model itself is explicitly noted as not yet available. missing for 10: a dedicated Codex SDK/library distinct from the general OpenAI Responses API, confirmation that Codex agent capabilities (not just chat completions) are exposed via SDK, independent developer corroboration of building against these SDKs.

   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [github] “A machine-readable description of the OpenAI REST API, authored in OpenAPI 3.1.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”
   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”

   proof ↗⚑ flag

   Conductor~partialprobed5/10

   Conductor documents an official REST-style API for managing cloud workspaces and sending/reading agent prompts, plus a hosted MCP server for AI clients, which supports building AI-native integrations. However, no dedicated client SDK packages (e.g., npm/python libraries) are evidenced, and a probe for an OpenAPI spec returned 404s, suggesting the 'SDK' is really just a raw API/MCP interface rather than a polished, language-specific SDK. missing for 10: official language SDK packages, OpenAPI/schema-based codegen support, independent hands-on confirmation of SDK usage.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [probe] “official MCP server documented at https://www.conductor.build/docs/api/mcp”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.conductor.build/openapi.json, https://www.conductor.build/swagger.json, https://www.cond…”

   proof ↗⚑ flag

9. ai-native userSubscribe to events via webhooks

   weight 2 · round drawn
   Codex—none0/10

   No evidence in the pack mentions webhooks or event subscription capabilities for Codex; the product exposes MCP servers, CLI, and cloud task integrations but nothing about outbound webhook events for AI-native consumers.

   ⚑ flag

   Conductor—none0/10

   The evidence pack documents a programmatic API and an MCP server for managing cloud workspaces, but nowhere mentions webhooks or any event-subscription mechanism for AI-native users to receive push notifications on workspace/task events.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”

   proof ↗⚑ flag

Agentic features

1. ai-native userGet AI-generated insights and suggestions from my data inside the product

   weight 2 · round to Codex
   Codex~partialclaimed6/10

   Codex generates AI-driven insights and suggestions specifically about code: it produces prioritized review findings, diffs, and summaries during automated reviews and delegated tasks (codex-docs-5, codex-docs-10, codex-docs-41, codex-docs-45), and can delegate to subagents for deeper investigation (codex-docs-35). However, this is scoped to code/repository data rather than general business or product data insights. Missing for 10: evidence of insight generation over non-code data sources, dashboards, or analytics-style summaries beyond code review findings.

   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Split up a larger investigation — subagents: Ask Codex to delegate focused work to specialized agents, then bring their findings back into t…”

   proof ↗⚑ flag

   Conductor~partialclaimed4/10

   Conductor orchestrates third-party coding agents (Claude Code, Codex, Cursor) that analyze the codebase and produce diffs, suggested changes, and PR reviews, which can be seen as data-driven suggestions, but Conductor itself does not document any native analytics/insights engine — the 'insight' generation is delegated entirely to the underlying agents. Missing for 10: no first-party insight/analytics feature, no evidence of Conductor synthesizing patterns or trends from user data beyond agent chat/diff output, no independent corroboration of this specific capability.

   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”
   • [claimed-docs] “Checkpoints | Session/workspace | Revert code and chat state to an earlier turn”

   proof ↗⚑ flag

2. ai-native userSet up automations that run autonomously in the background

   weight 2 · round drawn
   Codex✓fullclaimed7/10

   Codex cloud supports delegating longer tasks that run in isolated cloud environments in parallel, triggered from GitHub, GitLab, Linear, or Slack, and returning results (diff/PR) when ready — a clear background-automation workflow, and the CLI also supports non-interactive/repeatable workflows for scripted automation. Missing for 10: no documentation of scheduled/cron-style recurring triggers, and no independent/hands-on confirmation that long unattended background runs work reliably (community commentary focuses on interactive model quality/UX rather than background automation specifically).

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   proof ↗⚑ flag

   Conductor✓fullclaimed7/10

   Conductor's "routines" feature explicitly lets users run agents on a schedule or via GitHub Action, and cloud workspaces continue running autonomously ("agents keep working after you close your laptop") without requiring step-by-step confirmation. This directly matches background, autonomous automation for an AI-native user. Missing for 10: independent/hands-on confirmation that routines work reliably in practice, and more detail on scheduling configuration options beyond the changelog mention.

   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”

   proof ↗⚑ flag

3. ai-native userDelegate tasks to a built-in AI assistant inside the product

   weight 3 · round drawn
   Codex✓fullclaimed8/10

   Codex documents explicit task delegation to its built-in agent, both for long-running cloud tasks ('Delegate a longer task and return when it is ready') and for sub-agent delegation within a session ('Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session'), backed by detailed CLI/cloud docs. Missing for 10: independent hands-on verification specifically of the subagent delegation flow (community evidence discusses general agent quality/UX but not this feature directly).

   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Split up a larger investigation — subagents: Ask Codex to delegate focused work to specialized agents, then bring their findings back into t…”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”

   proof ↗⚑ flag

   Conductor✓fullcommunity8/10

   Conductor lets users delegate coding tasks to agents (Claude Code, Codex, Cursor, OpenCode) that run inside its own workspaces, autonomously testing repos, running builds, and continuing work unattended, with checkpoints and review flow built into the product (conductor-docs-1, -17, -20, -29, -32). Community reports confirm the agent runs live inside the app during real use (conductor-comm-7, conductor-comm-15). Missing for 10: independent benchmarking of assistant quality/reliability beyond docs and mixed anecdotal UX feedback (conductor-comm-9).

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”
   • [community] “I have been imagining something like this would be perfect for working with Claude Code... This feels like just a nice clean simple extensio…”
   • [community] “Your messages are just between you and Claude Code — it all runs on your local Claude Code installation via the SDK.”

   proof ↗⚑ flag

4. ai-native userOperate the product with natural-language commands

   weight 2 · round drawn
   Codex✓fullcommunity8/10

   Codex CLI, IDE extension, cloud, and web surfaces are all operated by natural-language prompts/chats — e.g. starting tasks from prompts, resuming chats, delegating subagents, pasting images into the composer, and non-interactive `codex exec` for scripted natural-language instructions — all documented as the primary interaction mode across surfaces. Community threads corroborate heavy real-world use of this conversational/agentic workflow, even amid quality complaints about model performance. missing for 10: independent benchmarking specifically of natural-language command comprehension/robustness (community evidence is about overall agent quality/speed, not NL parsing specifically).

   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “Bring visual context into the prompt — codex --image: Pass an error screenshot, architecture diagram, or design reference with the first pro…”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”

   proof ↗⚑ flag

   Conductor✓fullprobed8/10

   Conductor's entire interaction model is natural-language chat with coding agents (Claude Code, Codex, Cursor, OpenCode) that can autonomously test, build, and edit without step confirmation, and it exposes a hosted MCP server so ChatGPT/Claude/Codex or other AI clients can manage workspaces via natural language, plus an API to send prompts and read agent replies. missing for 10: independent/hands-on validation of natural-language command reliability beyond vendor docs.

   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”
   • [probe] “official MCP server documented at https://www.conductor.build/docs/api/mcp”

   proof ↗⚑ flag

Api quality

1. ai-native userExplore an interactive API reference with runnable examples

   weight 2 · round to Codex
   Codex~partialclaimed5/10

   The evidence shows OpenAI's general API reference (developers.openai.com) has runnable, per-language code samples with live examples, which an AI-native user could explore. However this is the general OpenAI Responses API reference, not a Codex-specific interactive API reference, and Codex itself is documented as a CLI/agent product rather than an API with its own dedicated reference docs. Missing for 10: a Codex-specific API reference page, evidence of interactivity beyond code-sample selection (e.g., live sandbox execution), and any Codex-specific documentation of this reference.

   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor has documented API endpoints and an MCP server, so an interactive API reference with runnable examples is a plausible feature, but the evidence pack shows no such reference exists — the docs page is static markdown and probes for OpenAPI/Swagger specs all returned 404.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.conductor.build/openapi.json, https://www.conductor.build/swagger.json, https://www.cond…”

   proof ↗⚑ flag

2. ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)

   weight 2 · round to Codex
   Codex~partialclaimed4/10

   OpenAI publishes a machine-readable OpenAPI 3.1 spec for its REST API (codex-gh-9) and Codex can be used via that API (codex-gh-4), but the evidence never confirms this spec explicitly covers or is dedicated to Codex-specific endpoints, nor is there a direct 'download spec' link tied to Codex docs. missing for 10: a Codex-specific OpenAPI/spec file, explicit download instructions, or confirmation the general OpenAI OpenAPI spec includes Codex CLI/agent endpoints.

   • [github] “A machine-readable description of the OpenAI REST API, authored in OpenAPI 3.1.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor documents a REST-like API and an MCP server, but a direct probe for machine-readable OpenAPI/Swagger specs at standard locations returned 404 on all candidate paths, and no evidence pack item links to a downloadable spec file.

   • [probe] “PROBE openapi: all candidate paths 404 (https://www.conductor.build/openapi.json, https://www.conductor.build/swagger.json, https://www.cond…”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”

   proof ↗⚑ flag

3. ai-native userTest against a sandbox environment without touching production data

   weight 1 · round drawn
   Codex~partialcommunity6/10

   Codex offers isolated cloud task environments and CLI sandbox controls (writable roots, permission gating) that keep agent actions contained rather than acting directly on a live system, which functions as a sandbox layer for testing changes. However, there's no explicit documentation of test-vs-production data separation, and a community report raises unresolved concerns about the sandbox reading sensitive filesystem data without asking. Missing for 10: explicit production-data isolation guarantees, first-party documentation addressing the raised sandbox-safety concern, and independent verification that isolated environments never touch real prod data.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [community] “Does that version of Codex still read sensitive data on your file system without even asking? Just curious. [links to github.com/openai/code…”

   proof ↗⚑ flag

   Conductor~partialcommunity6/10

   Conductor's core architecture creates isolated workspaces (separate git worktrees, branches, cloud sandboxes) so each agent task runs independently without touching the main/production branch (conductor-docs-2, conductor-docs-20, conductor-docs-27, conductor-docs-29), and community users confirm the git-worktree-based isolation (conductor-comm-1, conductor-comm-17). However, this isolation is code/branch-level, not explicitly a data-layer sandbox (e.g., staging DB, mock services), and one community report notes full GitHub write-access requirements that undercut a clean 'no touching production' guarantee (conductor-comm-5, conductor-comm-6). Missing for 10: explicit handling/isolation of production data stores or environment variables, and confirmation that sandbox workspaces cannot inadvertently write to production systems.

   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [community] “Oh cool, I was already doing this with git worktrees but a ui for it would be handy.”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”
   • [community] “I was really excited to try this but this does NOT work the way I expected. I wanted a simple git worktree manager for my existing, already-…”

   proof ↗⚑ flag

4. ai-native userRely on versioned APIs with a documented deprecation policy

   weight 2 · round to Codex
   Codex~partialclaimed3/10

   There is a documented OpenAPI 3.1 spec and API reference (codex-gh-9, codex-docs-29) and one concrete example of a deprecation notice (codex mcp-server deprecated in favor of the Codex app server, codex-docs-23), showing some practice of versioning and deprecation. However, there is no comprehensive, documented deprecation policy (timelines, notice periods, version numbering scheme) covering the Codex/OpenAI API generally. Missing for 10: an explicit deprecation policy document, API version numbering scheme, and independent corroboration of adherence to it.

   • [github] “A machine-readable description of the OpenAI REST API, authored in OpenAPI 3.1.”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”

   proof ↗⚑ flag

   Conductor—none0/10

   There's an API and MCP server documented, but no evidence of API versioning scheme or a deprecation policy; probes show no OpenAPI spec found and no changelog/policy on version deprecation.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.conductor.build/openapi.json, https://www.conductor.build/swagger.json, https://www.cond…”

   proof ↗⚑ flag

1. ai-native userPerform bulk operations across many items at once

   weight 2 · round to Conductor
   Codex~partialclaimed6/10

   Codex supports running multiple cloud tasks in parallel across repos (codex-docs-1, codex-docs-3, codex-docs-6) and delegating focused work to specialized sub-agents within a session (codex-docs-13), which gives some bulk/parallel automation capability. However, there's no explicit evidence of a bulk operation primitive (e.g., batch-apply an action across many files/items/tickets in one command) — the parallelism described is task-level (multiple independent runs) rather than a documented 'operate over N items at once' feature. Missing for 10: explicit bulk/batch API or CLI verb for acting across many items in one invocation, and independent confirmation of large-scale parallel throughput in practice.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   proof ↗⚑ flag

   Conductor~partialclaimed7/10

   Conductor supports running many coding agents in parallel across isolated workspaces, and exposes a programmatic API plus scheduled/CI-triggered 'routines' that can create workspaces and send prompts at scale — a reasonable basis for bulk, automation-driven operations across many items. However, there's no documented UI for batch-selecting and acting on many existing workspaces at once (e.g., bulk archive/merge), and no independent evidence of large-scale parallel runs in practice. Missing for 10: explicit multi-item batch actions in the UI, evidence of scale/limits on parallel agents, and third-party corroboration of bulk automation workflows via the API or routines.

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Run multiple agents in one workspace when the work belongs on the same branch and should share the same files and context.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”

   proof ↗⚑ flag

2. ai-native userDefine rules that trigger actions automatically on events

   weight 3 · round to Conductor
   Codex—none0/10

   Codex supports triggering tasks from external events (GitHub/GitLab/Linear/Slack) and running non-interactive workflows, but there is no evidence of a user-defined rules engine that lets users specify arbitrary trigger conditions and automated actions (e.g., 'on X event, do Y') — this is closer to integration hooks than a rules/automation framework. missing for 10: evidence of a rules/trigger definition interface, conditional logic configuration, or event-to-action mapping system that users can author themselves.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   proof ↗⚑ flag

   Conductor~partialclaimed5/10

   Conductor's 'routines' feature lets agents run on a schedule or via GitHub Action trigger, which is a limited form of event-driven automation, but there's no evidence of a general rules engine supporting arbitrary event types (e.g., webhooks, file changes, custom conditions) or complex trigger-action definitions. Missing for 10: broader event-type support, custom rule/condition definitions, and hands-on evidence that routines fire reliably on GitHub events.

   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Conductor
   Codex—none0/10

   The evidence shows Codex can run in CI/scripts (codex exec), be triggered from GitHub/GitLab/Slack, and run cloud tasks, but there is no mention of a native recurring/scheduled job or cron-like trigger mechanism within Codex itself. Automation is triggered by external events or manual invocation, not scheduled recurrence.

   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”

   proof ↗⚑ flag

   Conductor✓fullclaimed6/10

   Conductor's changelog explicitly introduces 'routines' that let agents run on a schedule or via GitHub Action, directly matching the recurring-jobs/workflows story. However, this is a single brief changelog mention with no dedicated documentation page, configuration details, or community corroboration of the feature in practice. Missing for 10: dedicated docs on routine/schedule configuration, independent/hands-on confirmation, details on failure handling or monitoring of scheduled runs.

   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”

   proof ↗⚑ flag

4. ai-native userVersion, review, and roll back my automations

   weight 1 · round to Conductor
   Codex~partialclaimed4/10

   Codex's CLI includes a dedicated review command that inspects diffs/commits without modifying the working tree (codex-docs-10, codex-doces-41/45), and it operates within git repos so changes are inherently versioned and revertible via git; skills/plugins can be packaged as reusable automations (codex-docs-20/42). However, there is no documented mechanism to version, review, or roll back the automations/skills/workflows themselves (e.g., skill version history, rollback of a plugin config, audit trail for automation changes) — only code diffs are reviewed. Missing for 10: explicit versioning of skills/automations, a rollback UI/command for automation configs, and independent evidence of this workflow in practice.

   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”
   • [claimed-docs] “Use skills and plugins: Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without l…”

   proof ↗⚑ flag

   Conductor~partialclaimed6/10

   Conductor provides git-based versioning (separate branches/worktrees per workspace), diff review before merge/PR, and 'Checkpoints' to revert code and chat state to an earlier turn—covering version, review, and rollback at the workspace/agent-session level. However, the newer 'Routines' (scheduled/GitHub-Action automations) feature has no documented versioning, review, or rollback mechanism specific to the automation definitions themselves. Missing for 10: explicit version history/rollback for Routines/scheduled automations, independent hands-on confirmation of checkpoint reliability.

   • [claimed-docs] “Checkpoints | Session/workspace | Revert code and chat state to an earlier turn”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”

   proof ↗⚑ flag

Background execution

1. ai-native userHave a cloud agent build, test, and demo a feature end-to-end for my review

   weight 2 · round to Codex
   Codex✓fullcommunity8/10

   Codex cloud lets users delegate tasks that run in isolated cloud environments, inspect summaries/diffs, request follow-ups, and open pull requests for review, effectively building/testing/demoing changes end-to-end for user review (codex-docs-1,5,6,7,37). Community commentary corroborates real-world agentic task completion, though with performance/reliability caveats. Missing for 10: independent hands-on verification specifically of the cloud (not CLI) workflow's demo/test artifacts, and no explicit mention of a 'demo' step (e.g., live preview) beyond diff/PR review.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Start and review work from the web or Codex CLI.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [community] “Often Claude Code Opus 4.6, on hard enough problems, can do the impression of acting fast without really making progress. Then you spin the …”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”

   proof ↗⚑ flag

   Conductor✓fullclaimed7/10

   Conductor's cloud agents can autonomously test repos, update setup scripts, and run builds without step-by-step confirmation (conductor-docs-17, conductor-docs-32), continue working after the laptop closes (conductor-docs-20), and then help the user review the diff, open a PR, and merge (conductor-docs-21) — covering build, test, and review end-to-end for a feature. Missing for 10: no explicit 'demo' artifact (e.g., preview links/screenshots) beyond diff/PR review, and no independent/hands-on account confirming a full autonomous build-test-review cycle worked as described.

   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”

   proof ↗⚑ flag

2. developerDelegate longer-running coding tasks to run in the background in an isolated cloud environment

   weight 3 · round to Codex
   Codex✓fullclaimed7/10

   OpenAI's docs describe a dedicated Codex cloud mode that runs tasks in isolated cloud environments, in parallel, triggered from web/GitHub/GitLab/Linear/Slack, with configurable repo setup and a workflow to inspect diffs/PRs on completion, plus a CLI command (`codex cloud`) to submit and later pull results locally — squarely matching the story of delegating longer background tasks to an isolated cloud environment. missing for 10: independent or hands-on community corroboration specifically validating the cloud/background execution feature (community evidence in the pack discusses CLI/app UX and model quality, not the cloud delegation flow itself).

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [github] “If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.”
   • [github] “If you are looking for the <em>cloud-based agent</em> from OpenAI, <strong>Codex Web</strong>, go to <a href="https://chatgpt.com/codex">cha…”

   proof ↗⚑ flag

   Conductor~partialcommunity7/10

   Docs describe a dedicated 'cloud workspace' feature where agents run in isolated sandboxes that 'spin up in seconds' and 'keep working after you close your laptop,' can test repos/run builds unattended, and continue processing PR checks while 'asleep' (conductor-docs-20, conductor-docs-17, conductor-docs-11, conductor-docs-13). However, community reports describe the core product as creating an isolated git worktree locally rather than a cloud container, contrasting it with Codex's cloud sandbox (conductor-comm-17, conductor-comm-6), suggesting the cloud-isolation capability may be a newer/optional layer rather than the default experience. Missing for 10: independent hands-on verification that background cloud tasks are fully isolated/persistent, and clarity on whether cloud workspaces are the default vs. opt-in given local-worktree-first community accounts.

   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “PR comments and failing-check logs now load while a cloud workspace is asleep.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”
   • [community] “I was really excited to try this but this does NOT work the way I expected. I wanted a simple git worktree manager for my existing, already-…”

   proof ↗⚑ flag

3. developerConfigure a reproducible cloud environment with the dependencies and setup steps my repository needs

   weight 2 · round drawn
   Codex~partialclaimed6/10

   Codex Cloud docs state you can configure the dependencies, tools, variables, and setup steps each repository needs for isolated cloud environments, directly matching the story. However, there is no detail on how reproducibility is guaranteed (e.g., container images, caching, version pinning) or independent hands-on confirmation of this setup workflow. Missing for 10: concrete configuration file/schema details, reproducibility guarantees, and independent verification of the setup working as documented.

   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   proof ↗⚑ flag

   Conductor~partialclaimed6/10

   Docs show Conductor's cloud workspaces spin up sandboxes, check for needed tools/credentials, and let agents edit install/setup scripts and run builds automatically, which supports configuring an environment with the right dependencies (conductor-docs-17, conductor-docs-20, conductor-docs-32, conductor-docs-33). However there's no explicit first-party description of a declarative, versioned environment-config file (e.g., a devcontainer-style spec) guaranteeing reproducibility across runs/teammates, and no independent confirmation that these setup scripts persist reliably across sessions. missing for 10: explicit reproducible-config artifact/spec, independent verification that environment setup is consistent across workspace recreations.

   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”
   • [claimed-docs] “When you open Conductor, it checks for the tools and credentials it needs. If anything is missing, Conductor walks you through setup.”

   proof ↗⚑ flag

Parallel agents

1. ai-native userLaunch fleets of autonomous agents that work in parallel on different tasks for hours or days

   weight 2 · round to Conductor
   Codex~partialcommunity6/10

   Codex Cloud supports running multiple tasks in parallel in isolated cloud environments, triggered from GitHub/GitLab/Linear/Slack, and delegating longer tasks to return to later, which covers parallel/async agent work. However, there is no explicit evidence of orchestrating large 'fleets' of many simultaneous agents, no stated duration limits confirming multi-day autonomous runs, and community feedback highlights usage-limit throttling that would constrain sustained parallel/long-running fleets. missing for 10: evidence of fleet-scale orchestration (many concurrent agents), confirmed multi-day autonomous run duration, and independent confirmation that parallel tasks aren't throttled by usage limits.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “The main issue I have with Codex is that the best model is insanely slow, except at nights and weekends when Silicon Valley goes to bed... I…”

   proof ↗⚑ flag

   Conductor✓fullclaimed7/10

   Docs show Conductor explicitly designed for running multiple agents (Claude Code, Codex, Cursor, OpenCode) in parallel across isolated workspaces/worktrees, with cloud workspaces that 'keep working after you close your laptop' and 'routines' to run agents on a schedule or via GitHub Action, supporting long-running autonomous fleets. Community feedback focuses on GitHub permission/privacy concerns rather than disputing the parallel-autonomy capability itself. Missing for 10: independent/hands-on confirmation of agents actually running unattended for multi-day spans and evidence of fleet scale (e.g., dozens of simultaneous agents).

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Run multiple agents in one workspace when the work belongs on the same branch and should share the same files and context.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”

   proof ↗⚑ flag

2. developerRun several task attempts in parallel and compare results before choosing one

   weight 1 · round to Conductor
   Codex~partialclaimed6/10

   Docs confirm Codex cloud can run tasks in parallel in isolated cloud environments without tying up the local machine, and results can be inspected (summary/diff) before choosing to follow up or open a PR — this covers running multiple attempts and reviewing outcomes. However, there's no explicit documentation of a dedicated 'compare multiple attempts side-by-side' UI/workflow, and no independent/community evidence confirming this parallel-comparison workflow works well in practice. missing for 10: explicit side-by-side comparison UI documentation, independent hands-on confirmation of comparing parallel attempts.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   proof ↗⚑ flag

   Conductor✓fullprobed8/10

   Conductor's core design is running multiple coding agents in parallel, each in its own isolated workspace/git worktree with its own branch, files, and diff/review path, letting a developer inspect and choose before merging (docs-2, docs-27, docs-29, docs-21, probe-1). Community hands-on comments corroborate the git-worktree-based parallel workspace model (conductor-comm-1, conductor-comm-17). missing for 10: explicit first-party description of a side-by-side comparison UI across multiple simultaneous attempts (evidence shows parallel isolated workspaces and per-workspace diff/review, but not an explicit 'compare attempts' feature or independent review confirming the comparison workflow).

   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://www.conductor.build/llms.txt # Conductor > Conductor is a Mac app that lets you run many coding agents …”
   • [community] “Oh cool, I was already doing this with git worktrees but a ui for it would be handy.”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”

   proof ↗⚑ flag

Scheduled automation

1. ai-native userSet up always-on agents that run on schedules or triggers to maintain and fix my software autonomously

   weight 2 · round to Conductor
   Codex~partialclaimed5/10

   Codex cloud supports starting tasks from external triggers (GitHub/GitLab issues & PRs, Linear issues, Slack messages) and running them in parallel isolated environments, which covers the 'triggers' half of the story, but there's no evidence of a true schedule/cron-based always-on agent that proactively maintains a repo without an external event. Missing for 10: explicit scheduled/cron execution, evidence of continuous unattended monitoring/maintenance loops, and independent confirmation these triggers reliably run autonomous fixes end-to-end.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   proof ↗⚑ flag

   Conductor~partialclaimed6/10

   Conductor documents 'routines' that run agents on a schedule or via GitHub Action, plus cloud agents that keep working after you close your laptop and can autonomously test, fix, and rebuild repos without step-by-step confirmation — directly supporting always-on autonomous maintenance. However, the routines feature is only briefly mentioned in a changelog entry with no deep documentation of trigger types, monitoring, or failure-handling, and no independent/hands-on evidence confirms long-running unattended reliability. Missing for 10: detailed docs on trigger configuration (webhooks, cron specifics), evidence of long-term unattended reliability, and community confirmation of the scheduling/autonomy feature working in practice.

   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”

   proof ↗⚑ flag

Debugging

1. developerDebug issues and troubleshoot using natural-language queries

   weight 2 · round to Codex
   Codex~partialcommunity7/10

   Codex CLI docs show clear natural-language debugging workflows: exploring unfamiliar code, running local tools, passing error screenshots for context, and running dedicated code review that reports prioritized findings (codex-docs-8, codex-docs-9, codex-docs-10, codex-docs-12). However, community evidence shows mixed real-world reliability on agentic/coding tasks and no independent confirmation specifically validating debugging accuracy. Missing for 10: hands-on validation of debugging/troubleshooting accuracy, and independent case studies showing successful root-cause diagnosis via NL queries.

   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Pass an error screenshot, architecture diagram, or design reference with the first prompt, or paste an image into the interactive composer.”
   • [community] “Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic.”
   • [community] “Often Claude Code Opus 4.6, on hard enough problems, can do the impression of acting fast without really making progress. Then you spin the …”

   proof ↗⚑ flag

   Conductor~partialclaimed5/10

   Conductor orchestrates coding agents (Claude Code, Codex, Cursor) that support natural-language chat, and each workspace has its own terminal, diff, and chat interface, implying a developer could ask an agent to debug/troubleshoot via NL queries. However, there's no Conductor-specific documentation describing a dedicated debugging/troubleshooting NL workflow, error-log analysis, or diagnostic features beyond generic agent chat and build/test execution. Missing for 10: explicit docs on NL-driven debugging workflows, log/error analysis features, or examples of troubleshooting via chat distinct from general coding tasks.

   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”
   • [claimed-docs] “Checkpoints | Session/workspace | Revert code and chat state to an earlier turn”

   proof ↗⚑ flag

Feature implementation

1. developerTurn a tracked issue into a complete pull request end-to-end

   weight 3 · round to Codex
   Codex✓fullclaimed8/10

   Codex explicitly supports starting work from a tracked issue (GitHub, GitLab, Linear) in cloud environments, running the task, inspecting the diff/summary, and opening a pull request when done, covering the full issue-to-PR loop. missing for 10: independent hands-on confirmation of a full issue-to-merged-PR workflow succeeding end-to-end, and detail on how issue context/acceptance criteria are actually parsed.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   proof ↗⚑ flag

   Conductor✓fullclaimed7/10

   Docs show workspaces can be created directly from a GitHub issue (conductor-docs-12), agents run autonomously to implement, test, and build (conductor-docs-17, conductor-docs-20), and Conductor then helps review the diff, open a PR, merge, and archive the workspace (conductor-docs-21) — covering the full issue-to-PR loop. Missing for 10: independent/hands-on confirmation of the complete issue→PR flow (community evidence covers worktree/permissions concerns but not this specific workflow), and no example of a merged PR originating from an issue.

   • [claimed-docs] “Use Command + Shift + N or the `...` button next to `New workspace` to create a workspace from a branch, pull request, GitHub issue, or Line…”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”

   proof ↗⚑ flag

2. developerDescribe a feature or bug in plain language and have the agent implement or fix it across multiple files

   weight 3 · round to Codex
   Codex✓fullcommunity8/10

   Codex CLI and cloud docs describe the core loop of natural-language task description leading to autonomous file inspection, editing, running local tools, and producing a diff/PR (codex-docs-30, codex-docs-9, codex-docs-6, codex-docs-5), and community commentary corroborates it does real multi-file edits ('it edits the files and I can use the proper tooling', 'shockingly good... no worse than average L3-L4 engs') alongside some negative UX complaints that don't dispute the core capability. Missing for 10: independent benchmark/case-study evidence specifically confirming complex multi-file refactors across large codebases, and some community reports of it 'struggling with almost anything' create mild quality tension without rising to a concrete dispute.

   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”
   • [community] “Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic.”

   proof ↗⚑ flag

   Conductor~partialcommunity6/10

   Conductor orchestrates underlying coding agents (Claude Code, Codex, Cursor, OpenCode) that implement plain-language feature requests across files, with workspaces, diffs, and PR flows supporting this, and community feedback confirms it works as a Claude Code-like workflow wrapper. However, the actual code-generation quality depends entirely on the underlying agent, not Conductor itself, and no hands-on example of a multi-file feature/bug fix is shown in the evidence. missing for 10: a concrete hands-on example of Conductor implementing a described feature/bug across multiple files, and clarity on Conductor's own contribution versus the wrapped agent's capability.

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [community] “I have been imagining something like this would be perfect for working with Claude Code... This feels like just a nice clean simple extensio…”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”

   proof ↗⚑ flag

Maintenance automation

1. developerHave the agent write tests, fix lint errors, resolve merge conflicts, and update dependencies for me

   weight 3 · round to Codex
   Codex~partialcommunity6/10

   Codex CLI/cloud docs describe a general-purpose coding agent that can inspect code, edit files, run local dev tools, automate repeatable work, and review diffs before PRs — capabilities broad enough to plausibly cover writing tests, fixing lint issues, resolving conflicts, and updating dependencies (codex-docs-8, codex-docs-9, codex-docs-30, codex-docs-41). However, none of the docs explicitly name test-writing, lint-fixing, merge-conflict resolution, or dependency updates as supported workflows, and community feedback is mixed on real-world reliability for complex agentic tasks (codex-comm-3, codex-comm-13). missing for 10: explicit documentation/examples of test generation, lint-fix automation, merge-conflict resolution, and dependency-update workflows, plus hands-on confirmation these specific tasks succeed.

   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “Having used codex a fair bit I find it really struggles with … almost anything. However using the equivalent chat gpt model is fantastic.”

   proof ↗⚑ flag

   Conductor~partialclaimed5/10

   Docs confirm the underlying agents can test repositories, edit setup/install scripts, and run builds autonomously (conductor-docs-17, conductor-docs-32), which covers test-writing/fixing to some degree, but there is no explicit documentation or community evidence of lint-error fixing, merge-conflict resolution, or dependency updates as distinct capabilities. Missing for 10: explicit evidence of lint fixing, merge conflict resolution, and dependency-update automation.

   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”

   proof ↗⚑ flag

Codebase mapping

1. developerUnderstand how a codebase fits together to find where to start making changes

   weight 3 · round to Codex
   Codex~partialclaimed6/10

   Codex CLI docs explicitly mention exploring unfamiliar code and planning changes within a repository, and it can inspect code, run local dev tools, and review diffs/commits — supporting codebase orientation. However, there's no dedicated codebase-mapping/visualization feature, no evidence of dependency-graph or architecture-summary generation, and community feedback focuses on agentic task execution rather than comprehension aids. Missing for 10: dedicated codebase-map/architecture-overview feature, independent hands-on evidence of effectively onboarding to unfamiliar large codebases, and richer navigation/search tooling beyond terminal chat resume.

   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor's evidence focuses on orchestrating parallel coding agents, worktrees, and workspace management, not on codebase comprehension features; the only related item is a basic file-content search (⌘⇧F), which does not constitute understanding how a codebase fits together or where to start making changes.

   • [claimed-docs] “Search file contents in your current local project or cloud workspace with ⌘⇧F.”

   proof ↗⚑ flag

2. developerHave the agent map and explain an entire unfamiliar codebase without manually selecting context files

   weight 3 · round to Codex
   Codex~partialclaimed5/10

   Codex CLI docs explicitly state it can be started in a repository 'to explore unfamiliar code, plan a change, edit files, and run your local development tools' (codex-docs-9), implying the agent autonomously navigates the codebase rather than requiring manual file selection, and codex-gh-1 confirms it runs as an autonomous coding agent locally. However, there's no detailed documentation of how it builds a whole-codebase map/summary, no explicit 'explain codebase' feature, and no independent hands-on evidence confirming this works well on large unfamiliar repos. Missing for 10: dedicated codebase-mapping/summarization feature documentation, evidence of handling very large repos, and independent user reports validating this specific capability.

   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor's evidence focuses on orchestrating parallel agent workspaces, worktrees, git branches, and collaboration—not on any built-in whole-codebase mapping or explanation capability. The closest feature is manual file-content search (⌘⇧F), which requires the developer to search rather than having the agent autonomously map/explain the codebase.

   • [claimed-docs] “Search file contents in your current local project or cloud workspace with ⌘⇧F.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”

   proof ↗⚑ flag

Context management

1. developerHave the agent build and recall memory automatically across sessions

   weight 2 · round to Codex
   Codex~partialclaimed3/10

   Codex CLI supports `codex resume` to reopen or search past local chats in a repository, giving a limited form of session recall, but this requires manual user action rather than automatic memory building/recall across sessions. Missing for 10: evidence of automatic persistent memory (learned facts, preferences, or context) that Codex builds unprompted and recalls without explicit resume/search commands, and any cross-session synthesis beyond raw chat transcripts.

   • [claimed-docs] “Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”

   proof ↗⚑ flag

   Conductor—none0/10

   Evidence covers checkpoints (revert to earlier turn), static 'general preferences' for repo-wide instructions, and parallel workspace/session management, but nothing describes the agent automatically building or recalling memory across sessions (e.g., persistent knowledge base, learned context reuse). This is a fair axis for a coding-agent orchestration tool, so absence of evidence yields none.

   • [claimed-docs] “Checkpoints | Session/workspace | Revert code and chat state to an earlier turn”
   • [claimed-docs] “`General preferences` apply broad instructions to agents in a repository.”

   proof ↗⚑ flag

2. developerInclude multiple project directories in a single session for broader context

   weight 2 · round drawn
   Codex—none0/10

   No evidence in the pack describes Codex supporting multiple project directories or repositories being combined in a single session/context; documentation focuses on single-repository sessions, cloud tasks, and per-repository setup steps.

   ⚑ flag

   Conductor—none0/10

   Conductor's workspace model is built on git worktrees scoped to a single repository/branch per workspace (conductor-docs-27, conductor-docs-29), and there's no documentation of combining multiple project directories into one session. A community member explicitly requested multi-repo task support, implying it isn't currently available (conductor-comm-12).

   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [community] “I've been looking for a tool like this, that lets Claude operate on multiple repos... but all the tools for background/multiplexing are alwa…”

   proof ↗⚑ flag

3. developerAdd a project instructions file to set coding standards and conventions the agent follows

   weight 3 · round to Conductor
   Codex—none0/10

   The evidence pack covers Codex's CLI, cloud, MCP, and review features but contains no mention of a project-level instructions/config file (e.g., AGENTS.md or similar) for setting coding standards or conventions the agent should follow. This is a plausible and common capability for coding agents, but nothing in the pack documents or demonstrates it.

   ⚑ flag

   Conductor~partialclaimed4/10

   Docs mention 'General preferences' that 'apply broad instructions to agents in a repository,' which is the closest match to a project instructions/conventions file, but there is no detail on file format, location, or how it maps to underlying agents' native instruction files (e.g., CLAUDE.md). Missing for 10: documentation of the actual file/config mechanism, examples of setting coding standards, and independent confirmation it works across all supported agents (Claude Code, Codex, Cursor, OpenCode).

   • [claimed-docs] “`General preferences` apply broad instructions to agents in a repository.”

   proof ↗⚑ flag

Issue diagnosis

1. developerReproduce issues, narrow down root causes, and verify fixes

   weight 3 · round to Codex
   Codex✓fullclaimed7/10

   Codex CLI docs explicitly describe exploring unfamiliar code and running local dev tools to investigate issues, passing error screenshots for context, delegating focused investigation to subagents, and running dedicated reviews against uncommitted changes/commits/base branches to verify fixes before committing — covering reproduce, narrow-down, and verify steps. Missing for 10: no explicit 'reproduce a bug' walkthrough or first-hand/independent account of successfully diagnosing and fixing a real bug end-to-end with Codex.

   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Pass an error screenshot, architecture diagram, or design reference with the first prompt, or paste an image into the interactive composer.”
   • [claimed-docs] “Ask Codex to delegate focused work to specialized agents, then bring their findings back into the main terminal session.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”

   proof ↗⚑ flag

   Conductor~partialclaimed6/10

   Conductor provides isolated worktrees/workspaces where agents can run builds, tests, and setup scripts (conductor-docs-17, conductor-docs-32, conductor-docs-29), diff/PR review paths to verify fixes (conductor-docs-2, conductor-docs-21), and checkpoints to revert code/chat state when narrowing down a bad change (conductor-docs-18). These features support the reproduce→diagnose→verify loop, but the evidence is all first-party docs describing environment/orchestration features rather than direct debugging tooling (log inspection, stack traces, targeted bisection) or independent hands-on accounts of successfully reproducing/root-causing a bug. missing for 10: dedicated debugging/log-inspection features, independent user reports of using Conductor to isolate root causes or verify fixes end-to-end.

   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “Checkpoints | Session/workspace | Revert code and chat state to an earlier turn”
   • [claimed-docs] “Search file contents in your current local project or cloud workspace with ⌘⇧F.”

   proof ↗⚑ flag

Marketplace

1. developerEquip the agent with custom skills to perform specialized tasks

   weight 1 · round to Codex
   Codex✓fullclaimed7/10

   Codex CLI docs explicitly describe packaging repeatable instructions as "skills" and adding plugins to connect Codex to team tools/data from the CLI, directly matching the custom-skills story. Missing for 10: independent hands-on validation of skill creation/usage, and deeper documentation on skill authoring format/lifecycle beyond a single mention.

   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor orchestrates existing coding agents (Claude Code, Codex, Cursor, OpenCode) and offers 'general preferences' for broad instructions, but there's no evidence of a custom skills/plugin/tool system for equipping agents with specialized capabilities; a community request even notes the lack of 'custom tools' in its menu (conductor-comm-2).

   • [claimed-docs] “`General preferences` apply broad instructions to agents in a repository.”
   • [community] “It'd be great to change the default branch used for creating new workspaces. I'd like the ability to add custom tools to the 'Open in...' me…”

   proof ↗⚑ flag

2. engineering-leadIntegrate third-party partner-built agent apps into my workflows

   weight 1 · round to Conductor
   Codex~partialclaimed6/10

   Codex documents integration points for third-party ecosystem tools — triggering work from GitHub, GitLab, Linear, and Slack (partner platforms), and connecting to third-party MCP servers, plugins, and skills that give access to tools like Figma or a browser — which supports embedding partner-built capabilities into engineering workflows. However, the evidence is framed around Codex consuming tools/data sources rather than a curated marketplace of partner-built 'agent apps,' and there's no independent case study of a partner agent integration working end-to-end. Missing for 10: evidence of a partner/agent-app marketplace or certified third-party agent integrations, and independent verification of such integrations working in practice.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”
   • [claimed-docs] “Use it to give ChatGPT or Codex access to third-party documentation, or to let it interact with developer tools like your browser or Figma.”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Use skills and plugins: Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without l…”
   • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation, or t…”

   proof ↗⚑ flag

   Conductor~partialcommunity7/10

   Conductor natively integrates several third-party agent apps (Claude Code, Codex, Cursor, OpenCode) into its parallel-workspace workflow, with per-org connection configuration and subscription/API-key support, and even exposes its own MCP server so other agent clients can manage workspaces. However, community feedback shows requests for additional partners (Gemini CLI, Amazon Q) that aren't yet supported, indicating a fixed rather than open/extensible partner ecosystem. Missing for 10: an open plugin/marketplace model for arbitrary partner agents, and independent confirmation of seamless integration beyond the listed agents.

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”
   • [claimed-docs] “Sign in to your Cursor subscription for cloud workspaces.”
   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [community] “Love the design. does it build on electron? and will it support other code agents, like gemini cli, codex, opencode ext.”
   • [community] “Would be cool if I can use this with opencode, Amazon Q or whatever. I reckon the logic would be quite similar. Seen a few of these tools bu…”

   proof ↗⚑ flag

Team knowledge

1. engineering-leadCreate a shared workspace from my docs and repos as a common source of truth for the team

   weight 1 · round to Conductor
   Codex—none0/10

   Codex documents repo-level cloud environments, RBAC, and MCP connections to team tools, but no evidence describes a shared 'workspace' feature that unifies docs and repos into a common source of truth for a team; this is a plausible ask for an engineering tool but Codex's evidence only covers per-task cloud environments and repo configuration, not a persistent shared knowledge/workspace layer.

   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”

   proof ↗⚑ flag

   Conductor~partialclaimed4/10

   Conductor's cloud workspaces are shared with the whole organization and teammates can follow, reassign, or pick up the same workspace/chat, giving some sense of a shared team space tied to a repo (conductor-docs-24, conductor-docs-25, conductor-docs-16). However, there's no evidence of a workspace built from 'docs' (knowledge base, wiki, or design docs) alongside repos, or of any feature explicitly positioned as a team 'source of truth' beyond per-repo agent preferences. missing for 10: docs ingestion/aggregation into a workspace, explicit source-of-truth knowledge base feature, independent corroboration of team-wide shared-workspace usage.

   • [claimed-docs] “Workspaces and chats are shared with your organization, so a teammate can open the same workspace, follow the same conversation, and pick up…”
   • [claimed-docs] “browse everyone's work in **Home**, contribute to a teammate's chat, follow workspaces you care about, and hand work off with **Reassign to*…”
   • [claimed-docs] “Right-click the workspace and choose **Reassign to** to make a teammate responsible for it.”
   • [claimed-docs] “`General preferences` apply broad instructions to agents in a repository.”

   proof ↗⚑ flag

Tool integration

1. developerConnect the agent to workflow tools like Jira, Slack, and Google Drive to extend its context

   weight 3 · round to Codex
   Codex~partialclaimed6/10

   Codex explicitly supports starting work from Slack (and GitHub/GitLab/Linear) and lets users add local or remote MCP servers to connect to third-party tools/docs (e.g. Figma, browser), giving a generic mechanism to extend context to workflow tools. However, there is no explicit documentation of native Jira or Google Drive connectors—only Slack is named among the story's specific tools, with Jira/Google Drive requiring the generic (and for one variant, deprecated/experimental) MCP server pathway. Missing for 10: named Jira integration, named Google Drive integration, and confirmation that the current (non-deprecated) MCP mechanism is broadly used for these specific SaaS tools.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”
   • [claimed-docs] “Package repeatable instructions as skills, then add plugins to connect Codex to your team's tools and data without leaving the CLI.”
   • [claimed-docs] “Use it to give ChatGPT or Codex access to third-party documentation, or to let it interact with developer tools like your browser or Figma.”
   • [claimed-docs] “Model Context Protocol (MCP) connects models to tools and context. Use it to give ChatGPT or Codex access to third-party documentation, or t…”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [github] “Codex MCP Server Interface [experimental]: a JSON-RPC API that runs over the Model Context Protocol (MCP) transport to control a local Codex…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”

   proof ↗⚑ flag

   Conductor—none0/10

   Evidence shows Conductor integrates with GitHub and Linear (issue/branch creation) and exposes an MCP server for managing cloud workspaces, but there is no mention of Jira, Slack, or Google Drive integrations anywhere in the docs or community evidence.

   ⚑ flag

2. developerKick off agent tasks directly from GitHub, GitLab, Linear, or Slack

   weight 2 · round to Codex
   Codex✓fullclaimed8/10

   First-party docs explicitly state Codex cloud tasks can be started from GitHub pull requests, GitLab merge requests/issues, Linear issues, or Slack channels/threads, matching the story directly. Missing for 10: independent/hands-on verification of these specific integrations working in practice (community evidence covers CLI/app UX but not the GitHub/GitLab/Linear/Slack kickoff flows specifically).

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”

   proof ↗⚑ flag

   Conductor~partialclaimed5/10

   Conductor lets you create a workspace (kick off an agent task) from a GitHub branch, pull request, GitHub issue, or Linear issue, and can trigger agent runs via GitHub Actions/scheduled routines, but there is no evidence of GitLab or Slack integration for starting tasks. missing for 10: GitLab task-kickoff support, Slack task-kickoff support, and independent confirmation of these triggers working in practice.

   • [claimed-docs] “Use Command + Shift + N or the `...` button next to `New workspace` to create a workspace from a branch, pull request, GitHub issue, or Line…”
   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”

   proof ↗⚑ flag

Cross device continuity

1. developerStart a task on one device and continue it later from another device or browser

   weight 2 · round to Codex
   Codex✓fullclaimed8/10

   Codex supports starting tasks in the cloud from web/GitHub/GitLab/Linear/Slack, working in parallel cloud environments, and later resuming or continuing work from the CLI via 'codex cloud' (browse active/completed chats, submit/apply results) or 'codex resume' to reopen local chats, plus a shared MCP config across ChatGPT desktop, CLI, and IDE extension enabling cross-client continuity. missing for 10: independent hands-on confirmation of seamless state sync across devices/browsers, and no explicit mention of resuming a cloud-started task from a different physical device's browser session.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Start and review work from the web or Codex CLI.”
   • [claimed-docs] “Move work to Codex cloud — codex cloud: Browse active and completed chats, submit work to a configured environment, and apply the result to …”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “The ChatGPT desktop app, Codex CLI, and IDE extension share this configuration. Once you configure your MCP servers, you can switch among th…”

   proof ↗⚑ flag

   Conductor~partialclaimed6/10

   Cloud workspaces are shared with the organization and support handoff via 'Reassign to' and shared links, so a teammate (or the same developer on another device) can open a workspace and pick up where they left off, and cloud agents keep working after the laptop closes. However, evidence is framed around team collaboration/handoff rather than explicit single-user cross-device continuity, and local (non-cloud) workspaces are tied to the machine's worktree. missing for 10: explicit documentation of the same developer resuming a *local* task from a different device, confirmation of seamless single-user cross-browser/device session continuity, and independent hands-on confirmation of this specific workflow.

   • [claimed-docs] “Workspaces and chats are shared with your organization, so a teammate can open the same workspace, follow the same conversation, and pick up…”
   • [claimed-docs] “browse everyone's work in **Home**, contribute to a teammate's chat, follow workspaces you care about, and hand work off with **Reassign to*…”
   • [claimed-docs] “The link opens the workspace in Conductor for any member of the organization.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “Following is useful when someone else is assigned to the workspace but you want to keep it in your workflow.”

   proof ↗⚑ flag

Ide integration

1. developerView interactive diffs and share selected code as context from within my JetBrains IDE

   weight 1 · round drawn
   Codex—none0/10

   Evidence shows Codex's IDE extension explicitly targets VS Code, Cursor, and Windsurf (codex-gh-2), with no mention of JetBrains IDEs, interactive diff viewing within an IDE, or a 'share selected code as context' feature. The axis (IDE integration) is clearly applicable to Codex as a coding agent, but JetBrains-specific support and the described interactive-diff/context-sharing workflow are simply absent from the evidence pack.

   • [github] “If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor is presented as a standalone Mac app with its own workspace/diff/terminal UI (conductor-docs-2, conductor-probe-1), not a JetBrains IDE plugin; none of the docs, changelog, or community threads mention any JetBrains integration, extension, or plugin for viewing diffs or sharing context from within a JetBrains IDE.

   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://www.conductor.build/llms.txt # Conductor > Conductor is a Mac app that lets you run many coding agents …”

   proof ↗⚑ flag

2. developerChat with the coding assistant directly inside my IDE for contextual help

   weight 3 · round to Codex
   Codex✓fullcommunity8/10

   Codex explicitly offers an IDE extension for VS Code, Cursor, and Windsurf, plus a CLI usable within the terminal in your repo, both providing contextual chat/help with the codebase (edit files, run commands, review diffs). Community evidence confirms real-world usage of Codex CLI/app for editing and testing files in context, though some note UX friction compared to competitors. Missing for 10: deeper first-party documentation/screenshots of the IDE extension's chat UI specifically, and stronger independent hands-on corroboration of in-IDE chat quality.

   • [github] “If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”

   proof ↗⚑ flag

   Conductor✓fullcommunity7/10

   Conductor provides each task/workspace its own chat, terminal, diff and review path directly alongside the running coding agent (Claude Code, Codex, Cursor, OpenCode), letting a developer converse with the assistant in context of their code (conductor-docs-2, conductor-docs-27). Community reports confirm the chat works locally against Claude Code with no meaningful complaint about chat context/quality beyond stylistic preference (conductor-comm-9, conductor-comm-15). Missing for 10: no evidence of a native plugin embedding this chat inside third-party IDEs like VS Code/JetBrains (it's a separate Mac app), and no independent hands-on review of contextual-help quality beyond one HN thread.

   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [community] “There's a 'feel' to the way Claude Code outputs the text. And for input as well. Sadly, this is lost with conductor. I just don't feel as jo…”
   • [community] “Your messages are just between you and Claude Code — it all runs on your local Claude Code installation via the SDK.”

   proof ↗⚑ flag

Session management

1. developerReview diffs visually and run multiple sessions side by side in a desktop app

   weight 2 · round to Conductor
   Codex~partialcommunity5/10

   Codex ships a desktop app ("codex app"/Codex App page) and documents parallel task execution plus diff/summary inspection before merging, suggesting the underlying pieces exist, but the evidence never shows the desktop app UI actually presenting a visual diff viewer or multiple sessions arranged side by side. Community notes even flag basic desktop-app reliability issues (stuck on 'Loading projects...', Mac-only availability). Missing for 10: concrete documentation/screenshots of the desktop app's diff viewer, explicit multi-session/side-by-side UI description, and independent confirmation it works smoothly.

   • [github] “If you want the desktop app experience, run <code>codex app</code> or visit the Codex App page.”
   • [github] “If you want the desktop app experience, run <code>codex app</code> or visit <a href="https://chatgpt.com/codex?app-landing-page=true">the Co…”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”
   • [community] “Mac only. Again. Apple is great but this is OpenAI devs showing their disconnect from the mainstream.”

   proof ↗⚑ flag

   Conductor✓fullprobed8/10

   Conductor is a native desktop (Mac) app that runs multiple coding agents (Claude Code, Codex, Cursor, OpenCode) in parallel, each in its own workspace/branch/worktree with a dedicated diff and review path before opening a PR, and community users independently confirm the git-worktree-based parallel session model. Missing for 10: independent hands-on evaluation specifically praising the visual diff-review UI's quality/UX (only vendor docs describe the diff view) and no screenshots/video corroboration.

   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [probe] “PROBE llms.txt: HTTP 200 at https://www.conductor.build/llms.txt # Conductor > Conductor is a Mac app that lets you run many coding agents …”
   • [community] “Oh cool, I was already doing this with git worktrees but a ui for it would be handy.”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”

   proof ↗⚑ flag

2. engineering-leadManage multiple agent-driven coding sessions from one unified workspace

   weight 2 · round to Conductor
   Codex✓fullcommunity7/10

   Codex documents cloud parallel task execution across multiple repos/environments (codex-docs-1,3,6), a web/CLI dashboard to browse active and completed chats and apply results locally (codex-docs-15), and resuming/searching across sessions (codex-docs-11,24), which together support managing multiple concurrent agent sessions from a unified interface. However, evidence is vendor-documentation only with no independent hands-on confirmation of a true 'unified workspace' UX for an engineering-lead managing many sessions simultaneously, and some community comments note UX rough edges (codex-comm-9,18). Missing for 10: independent/hands-on verification of multi-session management at scale, and clearer detail on cross-session visibility/coordination for a lead overseeing a team's agents.

   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Run tasks in parallel without tying up your local machine.”
   • [claimed-docs] “Delegate a longer task and return when it is ready.”
   • [claimed-docs] “Browse active and completed chats, submit work to a configured environment, and apply the result to your local repository from the terminal.”
   • [claimed-docs] “Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [claimed-docs] “`codex resume`: Reopen a recent chat from the current repository, or search across local chats when you need to return to older work.”
   • [community] “I wish Codex App was open source. I like it, but there are always a bunch of little paper cuts that, if you were using codex cli, you could …”

   proof ↗⚑ flag

   Conductor✓fullcommunity8/10

   Conductor is explicitly built as a unified workspace for running multiple coding agents (Claude Code, Codex, Cursor, OpenCode) in parallel, each with its own workspace/branch/terminal/diff, plus team collaboration features (reassign, follow, shared workspaces) that support engineering-lead oversight. Community hands-on posts corroborate the parallel-agent workflow, though some raised concerns about permissions/data practices unrelated to the core multi-session management claim. missing for 10: independent lead-level testimony specifically on cross-team oversight at scale, and clearer evidence of a dashboard view aggregating all sessions' status for a lead.

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “Workspaces and chats are shared with your organization, so a teammate can open the same workspace, follow the same conversation, and pick up…”
   • [claimed-docs] “browse everyone's work in **Home**, contribute to a teammate's chat, follow workspaces you care about, and hand work off with **Reassign to*…”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [community] “I have been imagining something like this would be perfect for working with Claude Code... This feels like just a nice clean simple extensio…”
   • [community] “Oh cool, I was already doing this with git worktrees but a ui for it would be handy.”

   proof ↗⚑ flag

Terminal workflow

1. developerRun a coding agent locally from my terminal

   weight 3 · round to Codex
   Codex✓fullcommunity9/10

   Codex CLI is explicitly documented as a coding agent that runs locally in the terminal, with npm/standalone install, working against the local repository, editing files, running commands, and offering interactive TUI plus non-interactive exec mode — well corroborated by first-party docs and GitHub README, with community usage discussion confirming real-world use. Missing for 10: independent hands-on verification specifically of pure local terminal usage (most community commentary discusses model quality/UX rather than the local-run mechanics) and some caveats about performance/limits reported by users.

   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [github] “npm install -g @openai/codex”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”
   • [claimed-docs] “Install the Codex CLI with the standalone installer for macOS and Linux.”
   • [community] “Codex is my favorite UX for anything as it edits the files and I can use the proper tooling to adjust and test stuff... However lately the l…”
   • [community] “Genuinely excited to try this out. I've started using Codex much more heavily in the past two months and honestly, it's been shockingly good…”

   proof ↗⚑ flag

   Conductor~partialprobed7/10

   Conductor documents running local coding agents (Claude Code, Codex, Cursor, OpenCode) with per-task local git worktrees and a dedicated terminal per workspace, and community confirms it runs the agent locally via the local CLI/SDK install (conductor-comm-15, conductor-comm-17). However, hands-on reports show it isn't a pure lightweight local terminal wrapper—it requires GitHub OAuth/cloning rather than just running an existing local repo, and some users complain the local CLI 'feel' (e.g., Claude Code's native terminal UX) is lost inside Conductor's GUI (conductor-comm-6, conductor-comm-9). Missing for 10: independent confirmation that pure terminal-only (non-GUI) workflows are fully supported, and clearer first-party disclosure addressing the community concerns about local vs. cloud/GitHub dependency.

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [community] “Your messages are just between you and Claude Code — it all runs on your local Claude Code installation via the SDK.”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”
   • [community] “I was really excited to try this but this does NOT work the way I expected. I wanted a simple git worktree manager for my existing, already-…”
   • [community] “There's a 'feel' to the way Claude Code outputs the text. And for input as well. Sadly, this is lost with conductor. I just don't feel as jo…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://www.conductor.build/llms.txt # Conductor > Conductor is a Mac app that lets you run many coding agents …”

   proof ↗⚑ flag

2. developerRun the agent non-interactively in scripts for workflow automation

   weight 2 · round to Codex
   Codex✓fullclaimed8/10

   Docs explicitly describe running 'a non-interactive command in a repeatable workflow' and automating repeatable work without leaving the terminal, plus support for submitting work to configured environments from scripts (codex exec-style usage implied). Missing for 10: independent hands-on confirmation of non-interactive/CI usage and detailed exit-code/output-format documentation for scripting.

   • [claimed-docs] “Run a non-interactive command in a repeatable workflow.”
   • [claimed-docs] “Inspect code, make changes, run commands, and automate repeatable work without leaving your terminal.”
   • [claimed-docs] “Browse active and completed chats, submit work to a configured environment, and apply the result to your local repository from the terminal.”
   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”

   proof ↗⚑ flag

   Conductor~partialclaimed6/10

   Conductor exposes a programmatic API to create workspaces, send prompts and read agent replies, and supports 'routines' to run agents on a schedule or via GitHub Action, which enables non-interactive, scripted automation of the agent outside the GUI. However, this is all first-party documentation with no independent/hands-on confirmation, and Conductor is fundamentally a GUI-first Mac app rather than a CLI tool built for scripting. Missing for 10: independent verification that the API/routines work reliably in real automation pipelines, and clearer CLI-style invocation/flags for non-interactive use.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [claimed-docs] “Introducing routines! You can now run your agents on a schedule or via GitHub action.”
   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”

   proof ↗⚑ flag

1. ai-native userDo everything through the API that I can do in the UI

   weight 2 · round to Conductor
   Codex~partialcommunity3/10

   Codex ships rich CLI/UI-only capabilities (cloud tasks, resume/review, skills, plugins, MCP client integration) with no evidence these are exposed via a dedicated Codex API, and the general OpenAI API (RBAC, Responses API) is not shown to cover Codex-specific workflows; community evidence even confirms the latest gpt-5.3-codex model 'isn't available on the API yet,' a documented parity gap. Missing for 10: documented API endpoints for cloud task delegation, chat/session resume, MCP tool orchestration, and confirmation that current models/features are API-accessible at parity with CLI/UI.

   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”
   • [claimed-docs] “Create a model response — request/response reference with runnable code samples selectable per language: HTTP, Python, TypeScript, Go, Ruby,…”
   • [claimed-docs] “codex mcp-server is deprecated. Use the Codex app server instead. ... This page documents the deprecated command for existing integrations. …”

   proof ↗⚑ flag

   Conductor~partialprobed5/10

   Conductor documents a programmatic API and a hosted MCP server that let you create cloud workspaces, send prompts, and read agent replies, giving genuine API access to core agent workflows (conductor-docs-13, conductor-docs-14, conductor-docs-30, conductor-probe-4). However, the API is explicitly scoped to 'cloud workspaces' only, with no evidence it exposes local workspace/worktree management, collaboration features (reassign, follow, sharing), settings like port forwarding, or UI-specific conveniences (loadouts, sections, checkpoints) — and no OpenAPI spec is discoverable (conductor-probe-3), suggesting the API surface is narrower than the full UI. missing for 10: full parity coverage of local workspace/git-worktree operations via API, coverage of collaboration/organization features via API, and a public OpenAPI spec or independent confirmation of API completeness.

   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”
   • [claimed-docs] “Conductor's hosted Model Context Protocol (MCP) server lets ChatGPT, Claude, Codex, and other MCP clients manage your cloud workspaces.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically. Use it to do things like: Create workspaces, send prompts to the coding…”
   • [probe] “official MCP server documented at https://www.conductor.build/docs/api/mcp”
   • [probe] “PROBE openapi: all candidate paths 404 (https://www.conductor.build/openapi.json, https://www.conductor.build/swagger.json, https://www.cond…”

   proof ↗⚑ flag

2. ai-native userExport all of my data in open formats and leave

   weight 3 · round drawn
   Codex—none0/10

   No evidence of any data export feature or open-format export mechanism for chat history, project data, or configurations; Codex works with local files/git repos but there's no documented export/portability capability for user data (e.g., conversation history, settings) to leave the platform. Missing for 10: any documented data export tool, open-format export (JSON/Markdown dump), or data portability statement.

   ⚑ flag

   Conductor—none0/10

   Conductor stores workspace state, chat history, and cloud workspace data, but no evidence in the pack shows an explicit data-export feature or open-format export guarantee; while code lives in git worktrees (inherently portable), there's no documentation of exporting chats, settings, or cloud workspace metadata. Community threads even raise unresolved concerns about data practices and lack of transparency (conductor-comm-3, conductor-comm-5), reinforcing the absence of an export/leave story.

   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [community] “Love it! Even just simply freeing my main branch would be a big win so I can keep working as well. But no way to find out if there's any dat…”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”

   proof ↗⚑ flag

3. ai-native userRead the product's source under an open license

   weight 2 · round to Codex
   Codex~partialcommunity4/10

   The Codex CLI source lives in a public GitHub repo (openai/codex) and a community comment implies its openness lets users 'diagnose and file an issue' the way they can't with the closed-source Codex App, suggesting at least the CLI's code is publicly viewable. However, no evidence pack item states an explicit open-source license, and the App/cloud components are explicitly described as closed. missing for 10: explicit license file/name (MIT, Apache, etc.), confirmation the full product (not just CLI) is open, and independent corroboration beyond one forum remark.

   • [github] “Codex CLI is a coding agent from OpenAI that runs locally on your computer.”
   • [community] “I wish Codex App was open source. I like it, but there are always a bunch of little paper cuts that, if you were using codex cli, you could …”

   proof ↗⚑ flag

   Conductor—none0/10

   There is no evidence Conductor's source is available under any open license; it is distributed as a compiled Mac app with docs/API only, and a community comment explicitly contrasts it with an open-source alternative ('Crystal... unlike Conductor is open source'), indicating Conductor's source is not open.

   • [community] “Crystal can do all of this and more, and unlike Conductor is open source.”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Codex—none0/10

   Codex CLI runs locally but requires signing into a ChatGPT account or OpenAI API key, and the core inference/model and cloud environments are OpenAI-hosted only; there is no self-hosted backend option. A commenter explicitly wishes the Codex App were open source, implying it is not, which forecloses self-hosting the core product.

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [community] “I wish Codex App was open source. I like it, but there are always a bunch of little paper cuts that, if you were using codex cli, you could …”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor is a proprietary Mac app with a hosted cloud service and API/MCP server; there is no evidence of a self-hostable core product—no open-source repo, on-prem deployment option, or self-hosting docs are mentioned. Community even contrasts it unfavorably with 'Crystal,' which is explicitly noted as open source unlike Conductor, reinforcing that self-hosting isn't offered.

   • [community] “Crystal can do all of this and more, and unlike Conductor is open source.”
   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”

   proof ↗⚑ flag

Authentication

1. developerAuthenticate with an API key instead of an account login

   weight 2 · round to Conductor
   Codex~partialcommunity5/10

   GitHub docs confirm Codex CLI supports API key authentication as an alternative to ChatGPT account login, but note it 'requires additional setup,' and the account-login flow (Sign in with ChatGPT) is the recommended default. Missing for 10: detailed API-key setup documentation, first-party quickstart parity with account login, and independent confirmation that API-key auth is fully feature-equivalent (e.g. codex-comm-5 shows some newer models aren't even available via API yet).

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [community] “gpt-5.3-codex isn't available on the API yet — 'We are working to safely enable API access soon.'”

   proof ↗⚑ flag

   Conductor✓fullclaimed7/10

   Conductor explicitly supports 'bring your own subscriptions and keys' and lets you configure Claude Code, Codex, and Cursor connections to use an API key instead of a subscription/account login per organization. This directly satisfies the developer's need to authenticate via API key rather than an account login flow. missing for 10: independent/hands-on confirmation that API-key auth works end-to-end without any account sign-in step, and detail on whether Conductor's own app access also supports API-key-only login (vs. GitHub OAuth).

   • [claimed-docs] “Bring your own subscriptions and keys”
   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”

   proof ↗⚑ flag

2. engineering-leadAuthenticate through an enterprise identity or cloud platform for compliance and scalability

   weight 2 · round to Codex
   Codex~partialclaimed5/10

   Codex supports signing in with a ChatGPT Business/Enterprise/Edu account (codex-gh-3, codex-gh-7) and OpenAI's platform offers RBAC to scope access at org/project level (codex-docs-28), suggesting enterprise-grade authentication and access control exist. However, there is no explicit documentation of SSO/SAML/OIDC federation with enterprise identity providers (e.g., Okta, Azure AD) specific to Codex, nor details on how ChatGPT Enterprise auth ties into RBAC for Codex usage. Missing for 10: explicit SSO/SAML/OIDC integration docs, enterprise IdP federation details, and independent confirmation of compliance-grade auth flows for Codex specifically.

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Busi…”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”

   proof ↗⚑ flag

   Conductor—none0/10

   Evidence shows only GitHub OAuth/GitHub App authentication and per-organization agent connection settings (conductor-comm-13, conductor-comm-14, conductor-docs-23); there is no mention of SSO, SAML, OIDC, or enterprise identity provider integration for compliance/scale. missing for 10: SSO/SAML/OIDC support, enterprise IdP integration, admin/compliance controls tied to identity.

   • [community] “Right now the app uses GitHub's OAuth sign in which unfortunately doesn't allow for fine-grained permissions... We're switching our sign-in …”
   • [community] “Fixed! You can now give Conductor fine-grained GitHub repository access. Or, skip the integration and use your local GitHub CLI auth.”
   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”

   proof ↗⚑ flag

3. developerSign in with my existing product subscription plan to use the coding agent

   weight 2 · round to Codex
   Codex✓fullclaimed9/10

   GitHub docs explicitly recommend signing in with ChatGPT to use Codex under existing Plus, Pro, Business, Edu, or Enterprise subscription plans, with API key as an alternative for those without such plans, directly confirming subscription-based sign-in. missing for 10: independent hands-on confirmation of the sign-in flow itself (evidence focuses on capability descriptions rather than a walkthrough).

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Busi…”
   • [github] “Run codex and select Sign in with ChatGPT. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, …”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”

   proof ↗⚑ flag

   Conductor✓fullclaimed8/10

   Docs explicitly state you can 'bring your own subscriptions and keys' and sign in with existing Cursor, Claude Code, or Codex subscriptions rather than requiring a separate Conductor-specific plan, with per-organization control over subscription vs API key. Missing for 10: independent hands-on confirmation that subscription sign-in works smoothly across all supported agents (only vendor changelog/docs evidence).

   • [claimed-docs] “Bring your own subscriptions and keys”
   • [claimed-docs] “Sign in to your Cursor subscription for cloud workspaces.”
   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”

   proof ↗⚑ flag

4. developerSign in with a personal account to get free-tier access without managing API keys

   weight 1 · round to Codex
   Codex✓fullclaimed8/10

   Codex CLI explicitly recommends signing in with a ChatGPT account (Plus/Pro/Business/Edu/Enterprise) to use Codex without an API key, with API key usage noted as an alternative requiring additional setup. This directly matches the story of personal-account sign-in without managing API keys, though the exact free-tier scope/limits aren't detailed. Missing for 10: explicit confirmation of a genuinely free tier (vs. paid ChatGPT plans) and independent corroboration of the login flow's simplicity.

   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”
   • [github] “Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Busi…”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor's docs describe a 'bring your own subscriptions and keys' model where users must sign in to their own Claude Code, Codex, or Cursor subscription or supply an API key (conductor-docs-19, conductor-docs-23, conductor-docs-7); there is no mention of a free tier accessible purely via personal account sign-in without managing credentials. Community discussion also focuses on GitHub OAuth/permissions issues, not a free-tier access model.

   • [claimed-docs] “Bring your own subscriptions and keys”
   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”
   • [claimed-docs] “Sign in to your Cursor subscription for cloud workspaces.”

   proof ↗⚑ flag

Model choice

1. developerLet the tool automatically pick the best model for each task

   weight 1 · round drawn
   Codex—none0/10

   Evidence shows Codex lets users manually choose the model and reasoning effort ('Stay in control: Choose the model, reasoning effort, permissions...') rather than any automatic best-model-per-task selection; no docs or community evidence describe an automatic model-routing/selection feature tied to cost or task type.

   • [claimed-docs] “Stay in control: Choose the model, reasoning effort, permissions, and commands that fit the task.”
   • [community] “The main issue I have with Codex is that the best model is insanely slow, except at nights and weekends when Silicon Valley goes to bed... I…”
   • [community] “First thoughts using gpt-5.3-codex-spark in Codex CLI: Blazing fast but it definitely has a small model feel... It has to be prompted to do …”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor documents manual model selection via 'loadouts' and keyboard shortcuts to switch between chosen models, but there is no evidence of an automatic mechanism that picks the best model per task based on cost/performance tradeoffs.

   • [claimed-docs] “Pick a loadout of your favorite models to quickly switch between. It’s keyboard accessible too: change models (⌃⌘ 1-5), effort (⌘⇧/), speed …”
   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”

   proof ↗⚑ flag

2. developerChoose which underlying AI model powers my session from multiple providers

   weight 2 · round to Conductor
   Codex—none0/10

   Docs confirm Codex lets users 'Choose the model, reasoning effort, permissions' (codex-docs-31), but this refers to selecting among OpenAI's own Codex/GPT models, not switching between different AI providers (e.g., Anthropic, Google). No evidence shows Codex supports plugging in or selecting non-OpenAI models/providers within a session.

   • [claimed-docs] “Stay in control: Choose the model, reasoning effort, permissions, and commands that fit the task.”
   • [github] “We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
   • [github] “You can also use Codex with an API key, but this requires additional setup.”

   proof ↗⚑ flag

   Conductor✓fullcommunity8/10

   Conductor explicitly supports running Claude Code, Codex, Cursor, and OpenCode as interchangeable providers, with a 'loadout' UI and keyboard shortcuts to switch models per session, plus per-organization configuration of API key vs subscription for each provider. Community comments confirm interest in and some support for multi-agent/provider use, though no independent hands-on review specifically validates seamless mid-session switching. Missing for 10: independent/hands-on verification of the model-switching UX and confirmation across all listed providers beyond vendor docs.

   • [claimed-docs] “Conductor lets you run Claude Code, Codex, Cursor, and OpenCode in parallel.”
   • [claimed-docs] “Pick a loadout of your favorite models to quickly switch between. It’s keyboard accessible too: change models (⌃⌘ 1-5), effort (⌘⇧/), speed …”
   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”
   • [community] “Love the design. does it build on electron? and will it support other code agents, like gemini cli, codex, opencode ext.”
   • [community] “Would be cool if I can use this with opencode, Amazon Q or whatever. I reckon the logic would be quite similar. Seen a few of these tools bu…”

   proof ↗⚑ flag

1. ai-native userChoose where my data is stored (region/residency)

   weight 2 · round drawn
   Codex—none0/10

   No evidence in the pack mentions data residency, regional storage options, or geographic controls for where Codex data is stored; the pack covers RBAC, MCP, CLI features, and cloud task execution but nothing about choosing a storage region.

   ⚑ flag

   Conductor—none0/10

   No evidence anywhere in the pack addresses data residency, region selection, or storage location controls for cloud workspaces; community comments even highlight lack of disclosure about where data is sent.

   • [community] “Love it! Even just simply freeing my main branch would be a big win so I can keep working as well. But no way to find out if there's any dat…”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”

   proof ↗⚑ flag

2. ai-native userPrevent my data from being used to train AI models

   weight 3 · round drawn
   Codex—none0/10

   The evidence pack contains no mention of data-training opt-out controls, enterprise data usage policies, or privacy settings for excluding user data from model training; it covers CLI features, MCP, RBAC, and community sentiment but nothing about training-data exclusion.

   ⚑ flag

   Conductor—none0/10

   No documentation or policy statement anywhere in the evidence pack addresses training-data opt-out or data-usage controls; in fact community reports explicitly note 'no way to find out if there's any data sent to your servers' and 'zero disclosure of data practices,' underscoring the absence of any such privacy control.

   • [community] “Love it! Even just simply freeing my main branch would be a big win so I can keep working as well. But no way to find out if there's any dat…”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”

   proof ↗⚑ flag

3. ai-native userControl data retention and deletion

   weight 2 · round drawn
   Codex—none0/10

   No evidence pack items address data retention controls, deletion policies, or configurable retention windows for Codex; RBAC docs address access control, not retention/deletion. Missing for 10: any documentation of data retention settings, deletion APIs/workflows, or retention policy configuration.

   ⚑ flag

   Conductor—none0/10

   No documentation describes retention periods, data-deletion controls, or export/purge mechanisms for cloud workspace data; community feedback explicitly flags 'zero disclosure of data practices' and no way to verify what is sent to Conductor's servers.

   • [community] “Love it! Even just simply freeing my main branch would be a big win so I can keep working as well. But no way to find out if there's any dat…”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”
   • [claimed-docs] “The Conductor API lets you manage cloud workspaces programmatically.”

   proof ↗⚑ flag

4. ai-native userOpt out of telemetry and usage tracking

   weight 2 · round drawn
   Codex—none0/10

   No evidence in the pack mentions telemetry, usage tracking, data collection settings, or an opt-out mechanism for Codex; the docs and community threads cover features like MCP, CLI usage, and performance but never privacy/telemetry controls.

   ⚑ flag

   Conductor—none0/10

   No documentation or changelog entry describes any telemetry/usage-tracking settings or an opt-out mechanism; community commenters explicitly note there is 'no way to find out if there's any data sent to your servers' and 'zero disclosure of data practices,' confirming the absence of any documented privacy control for telemetry.

   • [community] “Love it! Even just simply freeing my main branch would be a big win so I can keep working as well. But no way to find out if there's any dat…”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”

   proof ↗⚑ flag

Data governance

1. engineering-leadOpt out of having my code and prompts used for AI model training

   weight 1 · round drawn
   Codex—none0/10

   No evidence in the pack addresses data usage or training opt-out policies for code/prompts; RBAC and MCP docs are unrelated to this axis. Missing for 10: any enterprise data-usage/training opt-out policy documentation, admin controls for opting out, or third-party confirmation of such a policy.

   ⚑ flag

   Conductor—none0/10

   No evidence anywhere in the pack of a data-usage/training opt-out policy or setting; in fact community reports explicitly complain about 'zero disclosure of data practices' and no way to find out what is sent to Conductor's servers, reinforcing the absence of any documented opt-out mechanism.

   • [community] “Love it! Even just simply freeing my main branch would be a big win so I can keep working as well. But no way to find out if there's any dat…”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”

   proof ↗⚑ flag

Pr review

1. developerHave the agent stage changes, write commit messages, create branches, and open pull requests

   weight 3 · round to Conductor
   Codex~partialclaimed6/10

   Codex docs explicitly describe inspecting diffs and opening a pull request when cloud work is ready (codex-docs-5), and CLI docs note reviewing changes 'before you commit or open a pull request' (codex-docs-45), implying git workflow integration. However, staging changes, writing commit messages, and creating branches are not explicitly documented as first-class agent actions — they are only implied via general local repo access and command execution (codex-docs-9, codex-docs-30, codex-docs-17). Missing for 10: explicit documentation of commit-message generation, branch creation, and staging as named agent capabilities, plus independent hands-on confirmation of full PR workflow automation.

   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Start Codex in a repository to explore unfamiliar code, plan a change, edit files, and run your local development tools.”
   • [claimed-docs] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”

   proof ↗⚑ flag

   Conductor✓fullcommunity8/10

   Docs explicitly state each task gets its own branch/worktree, agents can be given autonomy to test/build without confirmation, and Conductor 'helps you review the diff, open a pull request, merge, and archive the workspace' — covering branch creation, staging/commits (implied by agent workflow), diffs, and PR creation. Community evidence corroborates git worktree branch isolation and GitHub integration for PR workflows. Missing for 10: explicit first-party mention of 'commit message writing' as a distinct feature and independent hands-on confirmation of the full stage→commit→branch→PR pipeline working end-to-end.

   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “Create a new workspace with Command + N when work should have its own branch, files, running environment, and review path.”
   • [claimed-docs] “Conductor creates a separate working tree for each workspace. That lets agents work in parallel without editing the same files on disk.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”
   • [community] “Fixed! You can now give Conductor fine-grained GitHub repository access. Or, skip the integration and use your local GitHub CLI auth.”

   proof ↗⚑ flag

2. developerGet automatic code review with contextual feedback on every pull request

   weight 3 · round to Codex
   Codex~partialclaimed5/10

   Codex CLI/cloud ships a dedicated 'review' capability that inspects uncommitted changes, a commit, or a base branch and reports prioritized findings without touching the working tree, and cloud tasks can be kicked off from GitHub PRs and later opened as PRs. However, there is no evidence of an automatic, PR-triggered review bot that comments on every pull request without manual invocation. missing for 10: evidence of automatic triggering on every PR (e.g., GitHub App/webhook auto-review), evidence of inline PR comments, independent confirmation of review quality on real PRs.

   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Start work in Codex cloud from GitHub pull requests, GitLab merge requests and issues, Linear issues, or Slack channels and threads.”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”

   proof ↗⚑ flag

   Conductor—none0/10

   Conductor's evidence describes parallel agent orchestration, diffs, and human-facing review workflows (e.g., 'Conductor helps you review the diff, open a pull request' and PR comments loading from GitHub) but no automated code-review bot that posts contextual feedback on pull requests. No evidence of an AI reviewer analyzing PR diffs and commenting automatically.

   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “PR comments and failing-check logs now load while a cloud workspace is asleep.”

   proof ↗⚑ flag

3. developerInspect diffs and run checks to catch problems before merging

   weight 3 · round to Codex
   Codex✓fullclaimed8/10

   Codex CLI has a dedicated review command that inspects diffs against uncommitted changes, a commit, or a base branch, reporting prioritized findings without modifying the working tree, plus cloud/web flows to inspect summaries and diffs before opening a PR. Missing for 10: independent/hands-on corroboration of the review command's accuracy and any CI-integrated check-running beyond exec/scripts.

   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Review changes before they ship: Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized f…”
   • [claimed-docs] “Run a dedicated review against uncommitted changes, a commit, or a base branch. Codex reports prioritized findings without modifying your wo…”
   • [claimed-docs] “Inspect the summary and diff, request a follow-up, or open a pull request when the result is ready.”
   • [claimed-docs] “Compose with scripts and CI: Use Codex interactively or call codex exec from repeatable workflows and pipelines.”

   proof ↗⚑ flag

   Conductor~partialclaimed6/10

   Docs show each workspace has its own diff and review path, and Conductor explicitly helps you 'review the diff, open a pull request, merge' before finishing work, plus it surfaces PR comments and failing-check logs even while a cloud workspace sleeps, and agents can run builds/tests as part of setup. However, there's no detailed description of built-in linting/test-runner integration beyond agent-run builds, and no independent/hands-on confirmation that this catches real problems pre-merge. Missing for 10: dedicated CI/check-running feature docs, independent verification of diff/check accuracy, and coverage of how failing checks block or warn before merge.

   • [claimed-docs] “Each task gets its own workspace, branch, files, terminal, diff, and review path.”
   • [claimed-docs] “When the work is ready, Conductor helps you review the diff, open a pull request, merge, and archive the workspace.”
   • [claimed-docs] “PR comments and failing-check logs now load while a cloud workspace is asleep.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [claimed-docs] “You can also have an agent configure the computer for you: it can test your repositories, edit setup scripts, and run builds.”

   proof ↗⚑ flag

Safe execution

1. engineering-leadControl which external tools and integrations the agent is allowed to access

   weight 2 · round to Codex
   Codex~partialclaimed6/10

   Codex documents fine-grained control over external tool access at the session/repo level: engineers can add/remove local or remote MCP servers, inspect available tools before they're used, and set permission boundaries for edits/commands via /permissions (codex-docs-16, codex-docs-38, codex-docs-39, codex-docs-46). This gives an engineer meaningful control over which integrations the agent can reach, and RBAC exists for org/project-level API access (codex-docs-28), but that RBAC is about API/dashboard permissions, not specifically about restricting agent tool/integration access org-wide for a lead managing a team's Codex usage. Missing for 10: evidence of centralized, lead-enforced policy that restricts which MCP servers/tools individual developers can enable (vs. per-session self-configuration), and independent confirmation this control actually prevents unauthorized tool access in practice.

   • [claimed-docs] “Add local or remote MCP servers, authenticate when needed, and inspect the tools available to the current session before Codex uses them.”
   • [claimed-docs] “Connect external tools with MCP — codex mcp: Add local or remote MCP servers, authenticate when needed, and inspect the tools available to t…”
   • [claimed-docs] “Set the boundaries for each run — /permissions: Choose when Codex can edit files or run commands without asking, and inspect the active sand…”
   • [claimed-docs] “In the `codex` TUI, use `/mcp` to see your active MCP servers.”
   • [claimed-docs] “Role-based access control (RBAC) lets you decide who can do what across your organization and projects—both through the API and in the Dashb…”

   proof ↗⚑ flag

   Conductor~partialcommunity5/10

   Conductor lets an org configure agent connections per organization (choosing API-key vs subscription per agent) and, after community pushback over full GitHub OAuth access, added fine-grained GitHub repository permissions or local GitHub CLI auth as an alternative [conductor-docs-23, conductor-comm-13, conductor-comm-14]. However there's no documented allow-list/deny-list for arbitrary external tools, MCP servers, or third-party integrations beyond GitHub scopes and model provider choice, and the initial full-write-access design (comm-4, comm-5, comm-6) shows the control was originally coarse and only partially remedied. missing for 10: granular per-tool/integration allow-listing beyond GitHub and model provider, admin-level policy enforcement across the org, and independent verification that fine-grained access covers all agent-invoked external services (e.g., MCP servers).

   • [claimed-docs] “Configure cloud agent connections separately for each organization, and choose whether Claude Code, Codex, and Cursor use an API key or subs…”
   • [community] “Any way to have it not require full write access to your entire GitHub account?”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”
   • [community] “Right now the app uses GitHub's OAuth sign in which unfortunately doesn't allow for fine-grained permissions... We're switching our sign-in …”
   • [community] “Fixed! You can now give Conductor fine-grained GitHub repository access. Or, skip the integration and use your local GitHub CLI auth.”

   proof ↗⚑ flag

2. engineering-leadHave the agent operate inside a sandbox when interacting with code, tools, and network resources

   weight 2 · round to Codex
   Codex✓fullcommunity7/10

   First-party docs explicitly describe sandboxed execution: Codex lets you 'choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots' (codex-docs-17), and cloud tasks run in 'isolated cloud environments' with configurable dependencies/tools (codex-docs-1, codex-docs-4). This directly matches the engineering-lead's need for sandboxed code/tool interaction, though network-resource sandboxing specifics are not spelled out and there's no independent hands-on verification of sandbox robustness (a community comment raises but does not concretely confirm a sandbox-bypass issue). Missing for 10: explicit documentation of network-level sandbox controls, and independent/hands-on confirmation that the sandbox reliably contains tool/network access.

   • [claimed-docs] “Choose when Codex can edit files or run commands without asking, and inspect the active sandbox and writable roots before you continue.”
   • [claimed-docs] “Run tasks in isolated cloud environments, work in parallel, and start work from the web, GitHub, GitLab, Linear, or Slack.”
   • [claimed-docs] “Configure the dependencies, tools, variables, and setup steps each repository needs.”
   • [community] “Do people really want codex to have control over their computer and apps? I'm still paranoid about keeping things securely sandboxed.”

   proof ↗⚑ flag

   Conductor~partialcommunity5/10

   Conductor's cloud workspaces are explicitly described as spinning up in "sandboxes" and the agent can run builds/tests without step-by-step confirmation, suggesting isolated execution for cloud mode. However, the local mode (the primary use case per community feedback) uses plain git worktrees on the user's own machine with no described network/tool sandboxing, and early versions required full read-write GitHub account access with no disclosed data practices, which is the opposite of a hardened sandbox model (though later mitigated with fine-grained GitHub App permissions). Missing for 10: explicit sandbox isolation details (container/VM boundaries, network egress controls) for local workspaces, and independent confirmation that cloud sandboxes restrict network/tool access beyond marketing language.

   • [claimed-docs] “Sandboxes spin up in seconds, and agents keep working after you close your laptop.”
   • [claimed-docs] “The agent can test your repositories, update install and setup scripts, and run builds — without asking you to confirm each step.”
   • [community] “We create an isolated git worktree locally on your machine — whereas Codex (I believe) is running a container on the cloud.”
   • [community] “Any way to have it not require full write access to your entire GitHub account?”
   • [community] “Full read-write access required to all your Github account's repos. Not just code. Settings, deploy keys. The works... Zero disclosure of da…”
   • [community] “Right now the app uses GitHub's OAuth sign in which unfortunately doesn't allow for fine-grained permissions... We're switching our sign-in …”
   • [community] “Fixed! You can now give Conductor fine-grained GitHub repository access. Or, skip the integration and use your local GitHub CLI auth.”

   proof ↗⚑ flag

Security checks

1. engineering-leadSee license and public-code matching references for AI-suggested code

   weight 1 · round drawn
   Codex—none0/10

   No evidence anywhere in the pack mentions license detection, public-code matching, or provenance references for AI-suggested code; Codex's review features (codex-docs-10, -41, -45) only cover code quality/prioritized findings, not license/public-code attribution.

   ⚑ flag

   Conductor—none0/10

   No evidence anywhere in the pack of license compliance checks, public-code/plagiarism matching, or provenance references for AI-suggested code; Conductor's documentation focuses on orchestration, workspaces, and diffs/PRs but never mentions license or code-provenance scanning.

   ⚑ flag