Codex vs cubic

Agent access

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

   weight 2 · round to cubic
   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

   cubic✓fullprobed9/10

   cubic hosts a dedicated llms.txt file at docs.cubic.dev/llms.txt (confirmed via live probe returning HTTP 200 with a documentation summary), directly enabling agents to be pointed at agent-oriented docs; this is reinforced by MCP server and CLI docs designed for agent consumption. Missing for 10: no independent/community confirmation of an agent successfully using llms.txt in practice.

   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.cubic.dev/llms.txt # cubic documentation > cubic reviews code on GitHub and in local coding workfl…”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   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

   cubic~partialprobed6/10

   cubic automatically reviews PRs once installed (headless, event-triggered automation on GitHub) and ships a standalone CLI (`cubic review`) that can run local/pre-push checks, which could be scripted into CI. However, there's no explicit documentation of a CI/CD pipeline integration (e.g., GitHub Actions workflow, exit codes, non-interactive flags) confirming true headless CI usage beyond the GitHub-app webhook flow. missing for 10: explicit CI pipeline integration docs/examples, confirmation of non-interactive/exit-code behavior for CLI in automated pipelines.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   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

   cubic—none0/10

   All MCP-related evidence describes cubic acting as an MCP *server* that other coding agents/clients connect to (cubic-docs-15, cubic-docs-3, cubic-probe-3) — the reverse of this story, which asks whether a user can plug external MCP servers into cubic so it can consume their tools. No evidence shows cubic itself connecting to or invoking external MCP servers/tools.

   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving you…”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   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

   cubic✓fullprobed8/10

   cubic documents an official MCP server that lets a coding agent read review findings, codebase context, request PR reviews, triage issues, and even manage subscription/seats without leaving the MCP client, confirmed by a dedicated docs page (probe) and quickstart references. Missing for 10: independent/hands-on community confirmation that the MCP server works as described (all evidence is vendor docs).

   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving you…”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”

   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

   cubic✓fullprobed8/10

   cubic ships an official CLI (`cubic review`) that reviews local/uncommitted changes and generates fix prompts for coding agents, documented explicitly and confirmed by a docs probe; it also integrates with agent workflows via MCP. Missing for 10: independent hands-on verification of the CLI itself (community evidence covers other product aspects, not CLI usage) and broader CLI command documentation beyond the single review command.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   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

   cubic~partialprobed6/10

   cubic documents an MCP server (cubic-docs-15, cubic-probe-3) that lets an AI agent request PR reviews, read findings, and triage issues, plus an Analytics API (cubic-docs-20) for PR-level data and a CLI (cubic-probe-4) for local reviews — all documented, agent-drivable surfaces. However, probes for a formal public API spec (openapi/swagger) all returned 404 (cubic-probe-2), so there's no evidence of a comprehensive documented public REST/GraphQL API beyond these narrower interfaces. Missing for 10: a full public API reference/spec, broader programmatic control beyond analytics/MCP/CLI, and independent confirmation of API usage.

   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”

   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

   cubic—none0/10

   Cubic documents role-based access control for team subscription/settings (cubic-docs-47) and exposes an MCP server, Analytics API, and CLI that agents can connect to, but there is no evidence of issuing scoped or least-privilege API credentials/tokens specifically for an agent's use — no API key scoping, OAuth scope, or agent-specific credential mechanism is documented.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

   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

   cubic—none0/10

   cubic documents an MCP server, CLI, and an Analytics API, but there is no evidence of official language SDKs (e.g., Python/JS client libraries) for building against cubic programmatically; the OpenAPI probe also returned 404s across candidate paths, suggesting no formal SDK/API spec is published.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   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

   cubic—none0/10

   No evidence of any webhook subscription mechanism; cubic exposes an MCP server, CLI, and Analytics API but nothing describing event-driven webhooks for subscribing to updates. missing for 10: any documentation of webhook endpoints, event types, or subscription setup.

   ⚑ flag

Agentic features

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

   weight 2 · round drawn
   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

   cubic~partialcommunity6/10

   Cubic generates AI-driven insights from a user's own code/PR data via automated reviews, Ultrareview, AI-powered codebase scans, an AI wiki that indexes the codebase, and an analytics dashboard summarizing AI coding/review impact (cubic-docs-4,13,18,20,21,22). However, community hands-on feedback is mixed, with several users noting a large share of AI-generated comments are irrelevant or low-value (cubic-comm-3,9), tempering claims of consistently useful insights. Missing for 10: independent benchmarking of insight accuracy, and confirmation that analytics/wiki insights are broadly praised rather than just described in docs.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Ultrareview runs a longer review using cubic's most capable review models, which is useful for risky migrations, security-sensitive changes,…”
   • [claimed-docs] “The analytics dashboard shows how your team ships code across three lenses: AI coding usage, AI review impact, and delivery speed.”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”
   • [community] “I've tried something similar in the past. The concept is cool, but so far the solutions I've seen are not so useful in terms of comments qua…”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”

   proof ↗⚑ flag

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

   weight 2 · round to cubic
   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

   cubic✓fullclaimed8/10

   cubic ships several autonomous background automations: it auto-starts PR reviews on install (cubic-docs-4, cubic-docs-41), can auto-approve clean PRs under policy (cubic-docs-12, cubic-docs-35), runs codebase scans deploying many AI agents (cubic-docs-21), keeps an AI wiki current via rolling PRs (cubic-docs-23), does cross-repo checks (cubic-docs-37), and auto-purchases flex capacity to keep reviews running (cubic-docs-24) — all without manual triggering. Missing for 10: evidence of user-defined scheduled/cron-style custom automations beyond PR-triggered events, and independent hands-on confirmation that these autonomous flows run reliably unattended.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [claimed-docs] “cubic can approve clean pull requests automatically when your repository policy allows it. Start in shadow mode to see which PRs cubic would…”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   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

   cubic✓fullclaimed7/10

   Cubic ships a built-in AI chat/assistant experience where users can delegate tasks — asking chat to 'tour this PR', adding code to AI chat for contextual Q&A, requesting one-click fixes ('Fix with cubic') that get generated and pushed automatically, and interacting via PR comments to trigger reviews or fixes. This is a genuine in-product assistant, not just an external agent integration. Missing for 10: independent/hands-on validation specifically of the chat-delegation UX (community evidence only covers review-comment quality, not the assistant/chat delegation flow), and no detail on task-completion reliability or scope limits of delegated tasks.

   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [claimed-docs] “The chat sidebar helps you quickly understand and navigate your pull requests (PRs) with intelligent, context-aware assistance directly with…”

   proof ↗⚑ flag

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

   weight 2 · round to Codex
   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

   cubic✓fullclaimed7/10

   cubic supports natural-language interaction via PR comments and chat: users can type commands like '@cubic-dev-ai review this PR', ask chat to 'tour this PR', reply to comments for clarification, request fixes, and connect an MCP server so a coding agent can trigger reviews and manage settings conversationally. Missing for 10: independent/hands-on evidence validating the quality and reliability of these NL interactions, and no evidence of broader free-form command coverage beyond the documented set of trigger phrases.

   • [claimed-docs] “To review a PR that was opened _before_ you installed the app, comment: `@cubic-dev-ai review this PR`.”
   • [claimed-docs] “Reply to a review comment to ask for clarification”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Post this comment on GitHub to start a review: text theme={null} @cubic-dev-ai review this PR ”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [claimed-docs] “The chat sidebar helps you quickly understand and navigate your pull requests (PRs) with intelligent, context-aware assistance directly with…”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving you…”

   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

   cubic—none0/10

   cubic documents an Analytics API but the evidence pack shows explicit probe failures for OpenAPI/swagger specs (404s) and no mention of an interactive API reference or runnable examples anywhere in the docs.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”

   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

   cubic—none0/10

   The probe explicitly checked common OpenAPI spec locations and all returned 404, and there is no other evidence of a downloadable machine-readable API spec for cubic's Analytics API or other endpoints; only an llms.txt is present, which is not an OpenAPI/API spec equivalent.

   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [probe] “PROBE llms.txt: HTTP 200 at https://docs.cubic.dev/llms.txt # cubic documentation > cubic reviews code on GitHub and in local coding workfl…”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

   proof ↗⚑ flag

3. 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

   cubic—none0/10

   There is an Analytics API mentioned (cubic-docs-20) but no evidence of API versioning scheme or a documented deprecation policy anywhere in the docs; the OpenAPI probe even returned 404s for spec endpoints. missing for 10: versioning scheme documentation, deprecation policy, changelog/migration guides for API changes, any mention of API stability guarantees.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   cubic~partialclaimed6/10

   cubic supports some bulk-like operations — codebase scans that 'deploy thousands of AI agents to find bugs across your repository' (cubic-docs-21), cross-repo reviews that check for related changes across multiple repos (cubic-docs-37/46), and analytics/CSV exports of PR-level data across a team (cubic-docs-19, cubic-docs-20) — but these are review/scan/export operations, not a general-purpose bulk-action capability (e.g., batch-fixing or batch-approving many PRs/items at once) with independent confirmation of scale. Missing for 10: explicit documentation of a bulk-action command/API for acting on many PRs, issues, or files simultaneously, and independent/hands-on evidence corroborating the 'thousands of agents' claim at scale.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository. Link related repositories so reviews can chec…”
   • [claimed-docs] “You can export team member data as CSV from both [AI coding](/analytics/ai-coding#csv-export) and [De”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   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

   cubic~partialclaimed6/10

   cubic supports several rule-based automated actions triggered by events within its code-review domain: auto-review on new PR (cubic-docs-4/41), auto-approval of clean PRs per repository policy (cubic-docs-12/35), auto thread resolution when an issue is fixed (cubic-docs-27), custom agents enforcing org rules across PRs (cubic-docs-34), and a spend-limit trigger that auto-purchases extra capacity (cubic-docs-24/48), all configurable via cubic.yaml (cubic-docs-16/36). These are genuine user-defined rule→action automations, but they are scoped to the code-review/PR lifecycle rather than a general-purpose event/rule engine for arbitrary triggers and actions. Missing for 10: a generic rules/automation builder spanning non-review events, explicit UI for defining custom trigger conditions beyond built-in policies, and independent confirmation these automations behave reliably at scale.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic can approve clean pull requests automatically when your repository policy allows it. Start in shadow mode to see which PRs cubic would…”
   • [claimed-docs] “Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”
   • [claimed-docs] “Flex capacity keeps GitHub PR AI reviews running after your workspace uses its included reviewed-line capacity. You set a monthly spend limi…”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [claimed-docs] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round drawn
   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

   cubic—none0/10

   cubic is a code review/PR automation tool triggered by PR events, webhooks, or manual commands (e.g., @cubic-dev-ai review, cubic review CLI), but no evidence describes scheduling recurring jobs or workflows on a time-based cadence (cron-like automation). Codebase scans and wiki updates appear event/PR-triggered, not user-schedulable recurring jobs.

   ⚑ flag

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

   weight 1 · round drawn
   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

   cubic~partialclaimed4/10

   cubic.yaml (the config defining review behavior and custom agents) lives in the repo root, so it inherits git's native versioning and can be reviewed like any code change (cubic-docs-16, cubic-docs-11), but there is no dedicated changelog, rollback UI, or history feature specifically for cubic's automations/config themselves. Missing for 10: explicit rollback/version-history feature for automation configs, evidence of reviewing changes to cubic.yaml itself, dedicated UI for managing automation versions.

   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “**Custom agents**: Enforce your team’s coding standards”
   • [claimed-docs] “Create a repository named `cubic-config` in your organization and add a `cubic.yaml` file to the root directory. cubic automatically applies…”

   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

   cubic—none0/10

   cubic is an AI code-review platform: it reviews PRs, fixes flagged issues, generates PR descriptions, and can auto-approve clean PRs, but there is no evidence it autonomously builds a feature from scratch, runs tests, and produces a demo for review — it only acts on existing diffs/PRs authored by humans or other coding agents.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “By default, cubic pushes commits directly to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “cubic helps your team spend less time writing PR descriptions automatically by generating clear, concise summaries.”

   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 Codex
   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

   cubic—none0/10

   cubic is positioned as an AI code-review, codebase-scan, and wiki-generation tool, not a platform for users to launch autonomous agent fleets to work on arbitrary tasks for hours/days. 'Codebase scans deploy thousands of AI agents' (cubic-docs-21) is an internal review mechanism, not a user-directed fleet of autonomous agents working independently over long time horizons, and no evidence describes user-initiated multi-agent parallel task execution.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “**Custom agents**: Enforce your team’s coding standards”

   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 cubic
   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

   cubic~partialclaimed6/10

   cubic ships trigger-based automation — it auto-reviews every new PR, reacts to force-pushes, can auto-fix flagged issues, auto-approve clean PRs, and runs codebase-wide scans with 'thousands of AI agents' plus a self-updating wiki via rolling PRs — which covers autonomous, trigger-driven maintenance of software. However, there is no evidence of user-defined schedules (cron-like) or general-purpose 'always-on agent' configuration beyond PR/code-review events. Missing for 10: explicit schedule/cron-based agent triggers, evidence of autonomous fixes/maintenance outside the PR-review workflow, and independent confirmation these agents run continuously without human PR-based triggers.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic can approve clean pull requests automatically when your repository policy allows it. Start in shadow mode to see which PRs cubic would…”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “cubic now reviews the new changes after a force-push when it can safely compare them with a previously reviewed version.”

   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

   cubic~partialcommunity6/10

   cubic supports natural-language interaction for understanding and troubleshooting issues it finds in code review — e.g., replying to review comments for clarification, asking chat to 'tour this PR', adding code to AI chat with diff/codebase context, and its MCP server lets agents 'read review findings... and triage PR or codebase scan issues.' However, this is scoped to PR-review/bug-flagging conversations rather than general-purpose debugging of runtime errors or arbitrary issues outside the review flow. Missing for 10: evidence of open-ended debugging (e.g., stack trace analysis, runtime error investigation) beyond PR/code-review context, and independent hands-on confirmation that these NL Q&A features actually resolve real bugs (community comments dispute overall comment quality/bug-catching rate).

   • [claimed-docs] “Reply to a review comment to ask for clarification”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”

   proof ↗⚑ flag

Feature implementation

1. 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

   cubic~partialclaimed3/10

   Cubic is primarily a code-review platform that finds issues and can push targeted one-click fixes to specific flagged problems (docs-7, docs-44), and its CLI generates a fix prompt for external coding agents (docs-31) rather than implementing features itself. It does not document taking a plain-language feature/bug description and independently implementing changes across multiple files; that work is explicitly handed off to a separate 'coding agent' (docs-15, docs-30). Missing for 10: evidence of accepting an open-ended natural-language feature/bug description (not just a flagged review comment) and autonomously implementing multi-file changes, plus any hands-on validation of such end-to-end generation.

   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “By default, cubic pushes commits directly to your PR branch.”

   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

   cubic~partialclaimed3/10

   cubic can automatically fix issues it flags in review (e.g., 'Fix with cubic' pushes a fix commit, docs-7/44) which could cover some lint-style issues, but there is no evidence it writes tests, resolves merge conflicts, or updates dependencies — cubic is positioned as a review/fix-on-comment tool, not a general-purpose coding agent for these tasks. missing for 10: test generation, merge-conflict resolution, dependency updates, and any evidence beyond review-triggered lint/bug fixes.

   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “By default, cubic pushes commits directly to your PR branch.”

   proof ↗⚑ flag

Codebase mapping

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

   weight 3 · round drawn
   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

   cubic~partialclaimed6/10

   cubic's AI wiki auto-indexes the codebase into a searchable wiki with architecture diagrams and source-code links, and its MCP server/chat features let developers query the codebase and diffs for context (cubic-docs-22, cubic-docs-23, cubic-docs-15, cubic-docs-10), which directly supports understanding how a codebase fits together before making changes. Codebase scans (cubic-docs-21) add bug/vuln discovery but aren't about architectural navigation. Missing for 10: independent/hands-on validation that the wiki or chat actually helps developers locate where to start changes, and community evidence is silent on this specific capability (only comments on PR review quality exist).

   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   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

   cubic~partialclaimed6/10

   cubic's AI wiki automatically indexes the entire codebase and produces searchable wikis with architecture diagrams and source links, and codebase scans deploy AI agents across the whole repo — both let a developer get a full-codebase map/explanation without hand-picking context files. However, this is documented only in first-party docs with no independent hands-on validation of how well it 'explains' an unfamiliar codebase, and community commentary focuses on PR-review quality rather than the wiki/codebase-scan features. Missing for 10: independent/hands-on verification of the AI wiki's accuracy and usefulness, and community evidence specifically evaluating whole-codebase explanation quality.

   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”

   proof ↗⚑ flag

Context management

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

   weight 2 · round drawn
   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

   cubic~partialclaimed3/10

   Cubic maintains some persistent state — it compares force-pushed changes against previously reviewed versions and its AI wiki auto-indexes and keeps codebase docs current — but there's no documented feature describing agent 'memory' that is built and recalled across chat/review sessions in the way the story implies. missing for 10: explicit session-memory mechanism, evidence of recall in later interactions, independent confirmation of persistent context use.

   • [claimed-docs] “cubic now reviews the new changes after a force-push when it can safely compare them with a previously reviewed version.”
   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”

   proof ↗⚑ flag

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

   weight 2 · round to cubic
   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

   cubic~partialclaimed4/10

   Cubic's 'cross-repo reviews' feature lets teams link related repositories so a review can check shared APIs, schemas, or docs across them, which is the closest analogue to including multiple project directories for broader context — but this is scoped narrowly to PR review consistency checks, not a general chat/agent session that loads multiple directories for open-ended Q&A. Missing for 10: evidence of a chat/agent session (e.g., MCP or CLI) that lets a developer add multiple arbitrary project directories as context, and any hands-on confirmation of cross-repo context quality.

   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository. Link related repositories so reviews can chec…”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   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

   cubic~partialclaimed6/10

   cubic supports a `cubic.yaml` config file at the repo root (or a shared `cubic-config` repo) that acts as 'the source of truth for AI review behavior, ignore patterns, PR descriptions, and custom agents,' and 'Custom agents' are documented as a way to 'enforce your team's coding standards.' This is a project-level instructions/config mechanism the agent follows, though it's framed around PR review behavior rather than a general-purpose coding-standards instructions file for all agent interactions. Missing for 10: explicit documentation of a plain-text/markdown instructions file (like AGENTS.md-style) covering broader coding conventions beyond review/ignore rules, and independent confirmation that custom agents reliably enforce standards in practice.

   • [claimed-docs] “**Custom agents**: Enforce your team’s coding standards”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “Create a repository named `cubic-config` in your organization and add a `cubic.yaml` file to the root directory. cubic automatically applies…”

   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

   cubic~partialclaimed4/10

   cubic is fundamentally an AI code-review/PR platform: it can flag bugs during review (codebase scans, PR review), generate and push fixes ('Fix with cubic'), and auto-resolve threads when issues are fixed, which covers some root-cause flagging and fix verification. However there is no evidence of actual issue reproduction (running the app/tests to trigger a bug) or root-cause debugging via execution—cubic's analysis is static/AI-review based, not a runtime debugger. Missing for 10: reproduction of bugs via execution/testing, dynamic root-cause tracing, and independent verification of fixes beyond thread auto-resolution.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Enable automatic thread resolution to close findings when the issue is fixed”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”

   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

   cubic~partialclaimed4/10

   cubic supports 'custom agents' configured via cubic.yaml to enforce coding standards, which is a limited form of custom skill/persona equipping for the review agent, but this is scoped narrowly to code-review behavior rather than general-purpose specialized task skills. Missing for 10: documentation on creating arbitrary custom skills/tools beyond coding-standard enforcement, examples of diverse specialized tasks, and independent validation of the custom agents feature.

   • [claimed-docs] “**Custom agents**: Enforce your team’s coding standards”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”

   proof ↗⚑ flag

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

   weight 1 · round drawn
   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

   cubic~partialprobed6/10

   cubic documents concrete integrations with third-party agent apps - connecting ChatGPT Plus or Claude Code subscriptions for local reviews, exposing an MCP server so coding agents can pull review findings and request PRs, pushing fixes via coding agents, and Linear or Jira issue-analysis integration - showing real ecosystem hooks for partner-built agent tools. Missing for 10: a documented marketplace or catalog of certified partner agent apps, examples beyond the major AI vendors, and independent evidence confirming these integrations work smoothly in practice.

   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “By default, cubic pushes commits directly to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “cubic can automatically analyze your pull requests to see if they meet the requirements from your linked Linear or Jira issues.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”

   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 cubic
   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

   cubic~partialclaimed5/10

   cubic's AI wiki automatically indexes a repo's codebase into a searchable, shared wiki (with architecture diagrams) that's exported into the repo and kept current via PRs, giving teams a common source of truth derived from code — but this is scoped to repos, not to ingesting a team's existing docs into one workspace. Missing for 10: explicit support for importing/aggregating external docs, cross-repo/team-wide workspace view (only per-repo wiki + cross-repo review linking), and any independent evidence the wiki is actually used as a 'workspace' by teams.

   • [claimed-docs] “cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams…”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository.”
   • [claimed-docs] “Cross-repo reviews help cubic catch changes that need a matching update in another repository. Link related repositories so reviews can chec…”

   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

   cubic—none0/10

   cubic's documented integrations are limited to GitHub, an MCP server for coding agents, and ChatGPT/Claude Code subscriptions for local reviews; there is no evidence of connectors to Jira, Slack, or Google Drive for extending context.

   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [community] “As far as I can see, this doesn't directly integrate with github (we currently use coderabbit on github)? Is it on your timeline?”
   • [community] “Would be great to have support for GitLab also (have a project there that I would love to try this on and I can't switch it to GitHub)”

   proof ↗⚑ 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

   cubic~partialcommunity4/10

   cubic clearly supports triggering reviews and fixes from GitHub (PR comments like `@cubic-dev-ai review this PR`, 'Fix with cubic', auto-review on install) and links to Linear/Jira for issue-requirement checks, but there's no evidence of Slack integration and community comments explicitly note GitLab support is missing/requested, not confirmed. Missing for 10: documented Slack task-triggering, confirmed GitLab support, and independent corroboration that Linear integration goes beyond issue-analysis to actually kicking off agent tasks.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “To review a PR that was opened _before_ you installed the app, comment: `@cubic-dev-ai review this PR`.”
   • [claimed-docs] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [claimed-docs] “Post this comment on GitHub to start a review: text theme={null} @cubic-dev-ai review this PR ”
   • [claimed-docs] “cubic can automatically analyze your pull requests to see if they meet the requirements from your linked Linear or Jira issues.”
   • [community] “Would be great to have support for GitLab also (have a project there that I would love to try this on and I can't switch it to GitHub)”
   • [community] “It looks like graphite.dev has pivoted into this space too, which is annoying since they still don't have gitlab support after several years…”

   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

   cubic~partialclaimed3/10

   cubic's reviews, chat, and fix actions happen inside GitHub PR comments and threads (docs-29, docs-45, docs-7), which are cloud-hosted and thus technically accessible from any device/browser, but cubic never documents an explicit cross-device 'resume task' or session-continuity feature for a developer's own work-in-progress task. Missing for 10: explicit session/task persistence across CLI, IDE, and browser, documented device-handoff workflow, and any first-party or community confirmation of resuming an in-progress task on a new device.

   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”

   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

   cubic—none0/10

   cubic's docs describe CLI review, MCP server for coding agents, and an 'Add to AI chat' feature for selecting code with diff context, but none of this is documented as a JetBrains IDE plugin or in-IDE interactive diff viewer — the 'ide/' docs paths refer to CLI and agent/MCP setup, not JetBrains integration specifically.

   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   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

   cubic~partialclaimed5/10

   cubic offers chat-based interaction (an 'Add to AI chat' feature with diff/codebase context, a chat sidebar for PR navigation, and an MCP server that lets coding agents in the IDE read review findings), but these are mostly scoped to reviewing PRs/code review rather than a general-purpose in-IDE chat assistant for arbitrary contextual coding help. Missing for 10: evidence of a native IDE chat panel for general coding questions (not tied to PR/diff review), and independent hands-on confirmation of in-IDE chat quality.

   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “The chat sidebar helps you quickly understand and navigate your pull requests (PRs) with intelligent, context-aware assistance directly with…”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”

   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

   cubic~partialprobed5/10

   cubic ships an official local CLI (`cubic review`) that runs from the terminal to review uncommitted changes before push, and can connect to Claude Code/ChatGPT subscriptions for local reviews, but this is a review agent rather than a general-purpose coding agent that writes/edits code interactively in the terminal. Missing for 10: evidence of an interactive terminal coding-agent loop (code generation/editing, multi-turn task execution) beyond review-only CLI use.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   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

   cubic~partialprobed5/10

   cubic ships a CLI (`cubic review`) that reviews local/uncommitted changes and automatically reviews PRs on GitHub without manual intervention, both of which suggest it can be woven into automated workflows (docs-4, docs-8, docs-31, docs-41). However, there is no explicit documentation of a non-interactive/headless mode, CI pipeline integration, exit codes, or scripting flags for the CLI. missing for 10: explicit CI/script integration docs, non-interactive mode flags, exit-code/output-format guarantees for automation, independent evidence of scripted use.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “cubic automatically starts reviewing new pull requests in your selected repositories.”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

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

   weight 2 · round to cubic
   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

   cubic~partialprobed4/10

   cubic exposes some functionality outside the UI — an Analytics API for PR-level data (cubic-docs-20), an MCP server for reading review findings, requesting reviews, and even managing subscriptions/seats (cubic-docs-3, cubic-docs-15), and a CLI for local reviews (cubic-docs-8, cubic-probe-4) — but there is no general-purpose public API (openapi probes 404, cubic-probe-2) covering the full UI surface (codebase scans, AI wiki, cubic.yaml config, analytics dashboard CSV exports, custom agents, auto-approve settings). Missing for 10: a comprehensive REST/GraphQL API or OpenAPI spec covering all UI features, evidence of API parity for wiki/codebase-scan/config management, and independent confirmation that MCP+CLI+Analytics API together replicate full UI functionality.

   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”
   • [claimed-docs] “You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving you…”
   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”
   • [probe] “official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
   • [probe] “official CLI documented at https://docs.cubic.dev/ide/cli-review”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   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

   cubic~partialclaimed4/10

   cubic offers some data portability: CSV export of team analytics (cubic-docs-19), an Analytics API for PR-level data (cubic-docs-20), and AI wiki content exported as markdown files into the repo (cubic-docs-23). However, there's no evidence of comprehensive export covering all review history, comments, configs, or account data in open formats, nor any documented account deletion/migration path for 'leaving' the platform. Missing for 10: full account/data export (reviews, comments, configs), explicit data-portability policy, independent confirmation of export completeness.

   • [claimed-docs] “You can export team member data as CSV from both [AI coding](/analytics/ai-coding#csv-export) and [De”
   • [claimed-docs] “The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
   • [claimed-docs] “cubic exports the wiki as markdown files into a directory in your repo (default `.cubic/wiki`) and keeps them current through a rolling pull…”

   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

   cubic—none0/10

   No evidence in the pack indicates cubic's source code is open or available under any open license; it appears to be a closed, commercial SaaS/CLI product with only documentation exposed publicly. Missing for 10: any open-source repository, license file, or public source code reference.

   ⚑ 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

   cubic—none0/10

   cubic is presented as a hosted SaaS code review platform (GitHub app, cloud dashboard, analytics, flex capacity billing) with no documentation of a self-hostable core, on-prem deployment, or open-source release. Absence of any self-hosting evidence for an applicable axis (a code review tool could plausibly be self-hosted) means this is 'none'.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”
   • [claimed-docs] “Flex capacity keeps GitHub PR AI reviews running after your workspace uses its included reviewed-line capacity. You set a monthly spend limi…”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”

   proof ↗⚑ flag

Authentication

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

   weight 2 · round to Codex
   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

   cubic—none0/10

   No evidence in the pack mentions API key authentication as an alternative to account login; cubic's docs describe GitHub app installation, roles/permissions, and subscription management but nothing about API-key-based auth for developers. The OpenAPI probe also returned 404s, suggesting no documented API surface with key auth.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings.”
   • [probe] “PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api…”

   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

   cubic—none0/10

   The evidence pack shows role-based access control for team/subscription management (cubic-docs-47) but no mention of SSO, SAML, OAuth enterprise identity provider integration, or cloud IAM authentication anywhere in the docs or community items. missing for 10: SSO/SAML support, enterprise IdP integration (Okta/Azure AD/Google Workspace), cloud IAM authentication, any compliance certification tied to auth.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings.”

   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

   cubic~partialclaimed6/10

   cubic explicitly lets developers connect an existing ChatGPT Plus/Pro or Claude Code subscription to power local CLI reviews, which matches 'sign in with existing subscription to use the coding agent.' However, this only applies to local review via CLI, not the full agent/reviewer product, and there's no independent verification of this flow working in practice. Missing for 10: broader applicability beyond CLI reviews, and community/hands-on confirmation of the subscription linking process.

   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”

   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

   cubic—none0/10

   cubic is a code-review/PR platform with team subscriptions, seats, and flex-capacity billing; no evidence describes a personal-account sign-in path granting free-tier access without API key management—this pricing/auth model story is unaddressed in the pack.

   ⚑ 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

   cubic—none0/10

   Cubic's docs describe distinct manually-invoked review modes (standard review vs. Ultrareview) and let users connect their own ChatGPT/Claude subscriptions for local reviews, but there is no evidence the tool automatically selects the best model per task based on cost or complexity — mode selection is user-driven, not automatic.

   • [claimed-docs] “Ultrareview runs a longer review using cubic's most capable review models, which is useful for risky migrations, security-sensitive changes,…”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models, and typically takes a…”
   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [claimed-docs] “You set a monthly spend limit, and cubic buys extra reviewed-line capacity only when a review would otherwise be paused.”

   proof ↗⚑ flag

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

   weight 2 · round to cubic
   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

   cubic~partialclaimed5/10

   Cubic docs state you can "connect your existing ChatGPT Plus/Pro or Claude Code subscription to use its models for local reviews" via the CLI, showing some model-provider choice, but PR reviews and Ultrareview use cubic's own proprietary 'most capable review models' with no indication of choosing among alternative providers there. missing for 10: model choice for the core PR/Ultrareview review sessions (not just local CLI), a documented list of selectable providers, and independent confirmation of the feature working in practice.

   • [claimed-docs] “Connect your existing **ChatGPT Plus/Pro** or **Claude Code** subscription to use its models for local reviews.”
   • [claimed-docs] “Ultrareview runs a longer review using cubic's most capable review models, which is useful for risky migrations, security-sensitive changes,…”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models, and typically takes a…”

   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

   cubic—none0/10

   No evidence in the pack mentions data residency, region selection, or storage location controls for cubic; the docs focus entirely on code review, PR workflows, and analytics with no privacy/data-residency configuration options mentioned.

   ⚑ 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

   cubic—none0/10

   No evidence in the pack addresses data usage for AI model training, opt-out policies, or data privacy commitments — cubic's docs focus entirely on code review features with no mention of training data controls.

   ⚑ 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

   cubic—none0/10

   No evidence in the pack addresses data retention policies, deletion controls, or privacy settings for AI-native users; docs cover review features, analytics, wiki, and pricing but nothing on retention/deletion of data. Missing for 10: any documentation on data retention periods, deletion requests, or privacy controls.

   ⚑ 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

   cubic—none0/10

   No evidence pack item addresses telemetry opt-out or usage-tracking controls; cubic's docs cover review features, analytics dashboards, and RBAC but never mention a privacy/telemetry toggle. missing for 10: any mention of telemetry collection, opt-out settings, or privacy controls.

   ⚑ 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

   cubic—none0/10

   No evidence in the pack addresses data-privacy or AI training opt-out policies for code/prompts; nothing in the docs, changelog, or community discussion mentions this capability. missing for 10: any documentation of data usage policy, training opt-out settings, or privacy controls.

   ⚑ flag

Pr review

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

   weight 3 · round to Codex
   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

   cubic~partialclaimed4/10

   cubic can push fix commits directly to an existing PR branch and auto-generate PR descriptions/summaries (cubic-docs-30, cubic-docs-44, cubic-docs-26, cubic-docs-49), but its own docs show the developer still runs the initial git workflow (checkout -b, commit, push) to create the branch and open the PR (cubic-docs-51) — cubic is a review/fix layer, not an agent that autonomously stages changes, writes original commit messages, creates branches, or opens PRs from scratch. missing for 10: evidence of cubic independently creating a new branch, staging changes, and opening a brand-new pull request without a human first running git/opening the PR.

   • [claimed-docs] “By default, cubic pushes commits directly to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Generates PR descriptions based on code changes”
   • [claimed-docs] “cubic helps your team spend less time writing PR descriptions automatically by generating clear, concise summaries.”
   • [claimed-docs] “you can keep using normal Git commands exactly as before (e.g., `git checkout -b my-feature`, `git commit -m "message"`, `git push`). Using …”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”

   proof ↗⚑ flag

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

   weight 3 · round to cubic
   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

   cubic~partialcommunity6/10

   cubic's docs strongly document automatic PR reviews with contextual comments, fixes, follow-up chat, and PR descriptions (cubic-docs-4, cubic-docs-25, cubic-docs-29, cubic-docs-45, cubic-docs-26). However, community hands-on feedback in the same threads is mixed: some praise the contextual quality (cubic-comm-1, cubic-comm-7) while others report low signal quality and skepticism about the marketing stats (cubic-comm-9, cubic-comm-10), so the real-world contextual value is not uniformly corroborated. Missing for 10: independent third-party benchmark of comment relevance, and consistent community consensus on comment quality rather than mixed reports.

   • [claimed-docs] “Once installed, cubic automatically reviews new pull requests.”
   • [claimed-docs] “Comments on bugs and improvements in pull requests”
   • [claimed-docs] “Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues.”
   • [claimed-docs] “Ask follow-up questions about code changes without leaving the PR”
   • [claimed-docs] “Generates PR descriptions based on code changes”
   • [community] “This looks like a cool solve for this problem. Some of the other tools I tried didn't seem to contextualize the app, so the comments were su…”
   • [community] “I've been testing this for the last few months, and it is now much quieter than before, and even more useful.”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”
   • [community] “When I read '51% fewer false positives' followed immediately by 'Median comments per pull request cut by half' it makes me wonder how many t…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   cubic✓fullcommunity8/10

   cubic provides diff-focused PR review (hiding tests, force-push re-review), a CLI (`cubic review`) to check uncommitted changes before pushing, Ultrareview for deep multi-pass checks, and auto-fix/auto-approval gating before merge — directly matching 'inspect diffs and run checks before merging'. Community feedback corroborates real-world use but also raises concerns about comment relevance and false-positive rates, tempering confidence. Missing for 10: independent quantitative validation of bug-catch accuracy and resolution of noise/false-positive concerns raised by users.

   • [claimed-docs] “Run a review before you push to catch issues while you're working.... review your uncommitted changes: `cubic review`”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Ultrareview runs a longer review using cubic's most capable review models, which is useful for risky migrations, security-sensitive changes,…”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [claimed-docs] “The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
   • [claimed-docs] “cubic now reviews the new changes after a force-push when it can safely compare them with a previously reviewed version.”
   • [claimed-docs] “Focus on implementation changes by hiding test files from the PR diff and file tree.”
   • [claimed-docs] “Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
   • [community] “I've been testing this for the last few months, and it is now much quieter than before, and even more useful.”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”

   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

   cubic—none0/10

   Evidence shows cubic has RBAC for subscription/settings management (cubic-docs-47) and cubic.yaml config for review behavior (cubic-docs-16/36), but nothing documents an engineering-lead controlling which external tools, MCP servers, or integrations the cubic agent itself is permitted to access. Missing for 10: any admin-facing tool/integration allowlist or permission gate for the agent's external tool access.

   • [claimed-docs] “cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings.”
   • [claimed-docs] “`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, …”
   • [claimed-docs] “cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, an…”
   • [claimed-docs] “Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase …”

   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

   cubic—none0/10

   cubic's evidence covers PR review, bug/vulnerability detection, custom agents, analytics, and codebase scans, but there is no mention of license compliance checking or public-code/plagiarism matching references for AI-suggested code. Missing for 10: license detection features, public-code/match provenance references, any SCA or license-compliance tooling.

   ⚑ flag

2. developerGet contextual explanations and automatic fixes for security vulnerabilities

   weight 2 · round to cubic
   Codex~partialclaimed3/10

   Codex CLI has a dedicated review command that inspects uncommitted changes, commits, or branches and reports 'prioritized findings' (codex-docs-10, codex-docs-41, codex-docs-45), which could surface security issues, and as a general coding agent it can edit files/run commands. However, the review feature explicitly reports findings 'without modifying your working tree,' meaning it does not auto-fix, and no evidence specifically frames this as security-vulnerability detection/explanation with automatic remediation. missing for 10: explicit security-vulnerability scanning/explanation feature, evidence of automatic fix application (vs. just flagging), and any independent confirmation that Codex reliably identifies/fixes security issues.

   • [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] “Work against your local repository: Let Codex inspect files, make edits, and run the tools already installed on your machine.”

   proof ↗⚑ flag

   cubic~partialcommunity7/10

   cubic's docs show explicit support for finding vulnerabilities (codebase scans, Ultrareview for 'security-sensitive changes'), contextual explanations (chat sidebar, 'tour this PR', reply-to-comment clarification), and automatic fixes ('Fix with cubic' pushes a fix commit; CLI generates fix prompts for coding agents). However there is no vendor or independent evidence specifically validating fix quality/accuracy for security vulnerabilities, and community comments raise general skepticism about comment relevance and false-positive rates for AI review tools of this class. missing for 10: security-specific hands-on validation of fix correctness, independent benchmarking on vulnerability detection/fix accuracy.

   • [claimed-docs] “Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
   • [claimed-docs] “Ultrareview runs a longer review using cubic's most capable review models, which is useful for risky migrations, security-sensitive changes,…”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models”
   • [claimed-docs] “Ultrareview is cubic's deepest review. It runs a longer, multi-pass analysis using cubic's most capable review models, and typically takes a…”
   • [claimed-docs] “Click **Fix with cubic** on a review comment... cubic generates the fix and pushes it to your PR branch.”
   • [claimed-docs] “cubic can automatically fix issues identified during code review. Request a targeted fix with one click.”
   • [claimed-docs] “Ask chat to "tour this PR" for a step-by-step review of the changes and what to check.”
   • [claimed-docs] “Select code and choose **Add to AI chat** to ask about it with the diff and codebase as context.”
   • [claimed-docs] “Reply to a review comment to ask for clarification”
   • [community] “what I saw using 5-6 tools like this: PR description is never useful, they barely summarize file changes; 90% of comments are wrong or irrel…”
   • [community] “When I read '51% fewer false positives' followed immediately by 'Median comments per pull request cut by half' it makes me wonder how many t…”

   proof ↗⚑ flag