Codex vs Gemini CLI

Agent access

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

   weight 2 · round to Codex
   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

   Gemini CLI—none0/10

   No evidence Gemini CLI has any documented feature for consuming llms.txt or agent-oriented doc manifests; the only related probe shows llms.txt returning 404 on Google's own docs site, and none of the GitHub feature list or docs mention llms.txt support. GEMINI.md context files are a different, project-local mechanism, not agent-oriented web docs discovery.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”

   proof ↗⚑ flag

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

   weight 2 · round to Gemini CLI
   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

   Gemini CLI✓fullclaimed9/10

   Gemini CLI explicitly documents non-interactive scripting mode, structured/streaming JSON output flags for programmatic parsing, and GitHub Actions-based automation (PR reviews, issue triage, on-demand assistance), which together cover headless/CI use cases well. Missing for 10: independent hands-on confirmation specifically of CI pipeline reliability (community evidence focuses more on interactive agentic quality than CI usage).

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   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

   Gemini CLI✓fullclaimed8/10

   Gemini CLI documents first-party MCP server support: configuring servers in ~/.gemini/settings.json to add custom tools, a dedicated /mcp command, and explicit mention of connecting media-generation tools like Imagen/Veo/Lyria via MCP. This is corroborated by official docs listing /mcp among CLI commands. Missing for 10: independent hands-on verification of MCP tool usage specifically (community evidence covers general agentic reliability but not MCP integration itself), and more detail on server management/discovery UX.

   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”

   proof ↗⚑ flag

4. ai-native userUse an official CLI

   weight 2 · round drawn
   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

   Gemini CLI✓fullprobed9/10

   Gemini CLI is itself an official, first-party CLI product by Google with extensive documentation of its features (scripting, JSON output, MCP support, context files, non-interactive mode) and independent corroboration of active use, confirming it exists and functions as an official CLI tool for AI-native workflows. missing for 10: no fully independent third-party audit of CLI completeness beyond community anecdotes.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “gemini --include-directories ../lib,../docs”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [probe] “official CLI documented at https://developers.google.com/gemini-code-assist/docs/gemini-cli”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   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

   Gemini CLI~partialprobed5/10

   Gemini CLI documents CLI-level automation hooks — non-interactive scripting mode, `--output-format json`/`stream-json` for structured output, and MCP server configuration — which let an AI-native user drive it programmatically (gemini-cli-gh-6, gh-17, gh-18, gh-19). However, explicit probes for a formal public API/SDK (llms.txt, openapi.json) all returned 404, showing no dedicated documented API surface beyond the CLI itself. Missing for 10: a first-party REST/SDK API spec, official API reference docs, and independent confirmation of programmatic (non-CLI) usage.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

6. 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

   Gemini CLI—none0/10

   Evidence shows Gemini CLI abstracts away API key management entirely (sign in with Google account) rather than offering scoped or least-privilege credential issuance for agents; no docs mention credential scoping, permission boundaries, or token minting for agent use.

   • [github] “No API key management - just sign in with your Google account”

   proof ↗⚑ flag

7. 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

   Gemini CLI—none0/10

   The evidence pack documents CLI flags, MCP server extensibility, scripting output formats, and GitHub Actions integration, but contains no mention of an official SDK (e.g., a Node/Python/Go library) for programmatically building on Gemini CLI itself. Probes for API/OpenAPI specs also returned 404s, reinforcing the absence of such artifacts.

   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

8. 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

   Gemini CLI—none0/10

   No evidence of webhook subscription or event-push capability; Gemini CLI supports non-interactive scripting, MCP tool servers, and structured JSON output, but nothing about outbound webhooks or event subscriptions. Missing for 10: any webhook registration mechanism, event subscription API, or documentation of push notifications.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”

   proof ↗⚑ flag

Agentic features

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

   weight 2 · round to Codex
   Codex~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Gemini CLI!disputedcontradicted5/10

   Gemini CLI ships features that clearly aim at generating insights from a user's own data/codebase — querying and editing large codebases, natural-language debugging, automated PR review with contextual feedback, and issue triage (gemini-cli-gh-1, gh-3, gh-10, gh-11), and one community report praises its code review as catching bugs missed by humans (gemini-cli-comm-20). However, multiple hands-on reports directly contradict this, describing it as 'terrible at agentic stuff', getting stuck in loops, failing to edit/read files, and being 'useless as a coding assistant' that produces spaghetti code (gemini-cli-comm-10, comm-14, comm-15). missing for 10: independent benchmark confirming consistent quality of generated insights, resolution of the loop/failure reports, and evidence the insight-generation works reliably across data types beyond code.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”

   proof ↗⚑ flag

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

   weight 2 · round to Codex
   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

   Gemini CLI~partialcommunity6/10

   Gemini CLI documents non-interactive scripting mode and a GitHub Action integration that runs autonomously in the background (automated PR reviews, issue triage, on-demand @gemini-cli responses), which directly supports background automations. However, independent community reports describe agentic reliability problems (getting stuck in loops, failing simple file operations, ignoring GEMINI.md context) that undercut confidence in unattended/background runs actually completing correctly. Missing for 10: independent hands-on validation that scheduled/background automations run reliably end-to-end, and more detail on failure/retry handling in autonomous mode.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “@github List my open pull requests”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   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

   Gemini CLI!disputedcontradicted5/10

   Gemini CLI is itself billed as an agentic assistant with extensive task-delegation features (codebase queries, debugging, PR review/issue triage, operational automation via @gemini-cli mentions) per gemini-cli-gh-3/4/10/11/12/22. However, hands-on community reports concretely contradict reliable delegation: users report it is 'really really terrible at agentic stuff,' gets stuck in permanent loops, ignores GEMINI.md context, and in one case catastrophically deleted user files while apologizing for the failure.

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   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

   Gemini CLI!disputedcontradicted5/10

   Gemini CLI's entire premise is natural-language driven coding/agentic actions (querying codebases, debugging, automating PR/rebase tasks, custom GEMINI.md context) per gemini-cli-gh-1/3/4/9. However, multiple hands-on reports describe the NL-agent behavior failing badly in practice — getting stuck in error loops, botching file edits, ignoring GEMINI.md instructions, and in one case catastrophically deleting user data via misinterpreted commands.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   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

   Gemini CLI—none0/10

   No evidence of an interactive API reference with runnable examples; probes explicitly show no llms.txt or OpenAPI spec found, and no docs describe an interactive reference tool.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   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

   Gemini CLI—none0/10

   Probes explicitly show no OpenAPI/llms.txt spec is published (404s at all candidate paths), and no other evidence mentions a machine-readable API spec for Gemini CLI.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

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

   weight 1 · round to Codex
   Codex~partialcommunity6/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   No evidence pack items describe a sandbox/test environment isolated from production data for Gemini CLI; the only mention of 'sandbox' appears in an unrelated community comment describing another tool's architecture, not Gemini CLI's own testing environment. missing for 10: dedicated sandbox mode/documentation, evidence of isolation from production data, any hands-on confirmation of safe test environments.

   ⚑ flag

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

   weight 2 · round to Codex
   Codex~partialclaimed3/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   No evidence of versioned APIs or a documented deprecation policy for Gemini CLI; probes for llms.txt/openapi specs 404, and there is community evidence the tool itself was abruptly deprecated with no policy discussion (gemini-cli-comm-6/7/8), but no documentation of API versioning or deprecation commitments exists.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”
   • [community] “Welcome to the Google graveyard, Gemini CLI. Not that it will be missed much. Using it was the worst experience out of any harness.”
   • [community] “Google really can't help themselves but to have some internal re-org kill off a public thing people are actively using. It's honestly impres…”

   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

   Gemini CLI~partialcommunity6/10

   Gemini CLI supports scripting/non-interactive automation, multi-directory context inclusion, structured JSON output for pipelines, and GitHub Action integrations like automated issue triage (bulk labeling/prioritization) and PR review across a repo — all pointing to bulk/batch style operations. However there's no explicit documented 'batch process N files/items' feature or example, and community reports note the agent can get stuck in loops or fail simple multi-step tasks, raising doubts about reliability at scale. Missing for 10: explicit bulk-operation examples/documentation (e.g., batch renaming, mass refactor across many files) and independent evidence confirming reliable execution at scale.

   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “gemini --include-directories ../lib,../docs”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”

   proof ↗⚑ flag

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

   weight 3 · round to Gemini CLI
   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

   Gemini CLI~partialclaimed5/10

   Gemini CLI ships GitHub Action integrations that fire automatically on repo events (PR opened → automated review, issue created → automated triage, @mention → on-demand help), which is a form of event-triggered automation, plus non-interactive/scripted execution for pipelines. However there's no evidence of a general-purpose, user-defined rule/trigger engine (e.g., custom webhooks, cron-like conditions, arbitrary event types) within the CLI itself—only fixed GitHub-event integrations. Missing for 10: a generic rule-definition mechanism for arbitrary events, documentation of custom trigger conditions, and independent confirmation these automations work reliably (community notes reliability issues with agentic behavior).

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Run non-interactively in scripts for workflow automation”

   proof ↗⚑ flag

3. ai-native userSchedule recurring jobs or workflows

   weight 2 · round to Gemini CLI
   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

   Gemini CLI~partialclaimed4/10

   Gemini CLI supports non-interactive scripted runs and structured JSON output, which lets users wire it into external schedulers (cron, CI) for recurring automation, and its GitHub Action integrations (issue triage, PR review) imply repeatable, trigger-based workflows. However there is no first-party 'scheduled job' or cron feature documented within the CLI itself. Missing for 10: a native recurring-job/scheduler feature, explicit docs on scheduling cadence, and independent confirmation that scripted/CI-triggered runs work reliably for recurring automation.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”

   proof ↗⚑ 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

   Gemini CLI~partialclaimed4/10

   Gemini CLI offers conversation checkpointing to save and resume sessions (gemini-cli-gh-8), which provides a rudimentary rollback/resume mechanism, but there is no evidence of versioning, diffing, or reviewing automation scripts/workflows themselves, nor a dedicated rollback command for automations. missing for 10: explicit version history for automations, review/diff tooling, and a documented rollback mechanism beyond session checkpoints.

   • [github] “Conversation checkpointing to save and resume complex sessions”

   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

   Gemini CLI~partialcommunity4/10

   Gemini CLI documents cloud-adjacent automation via its GitHub Actions integration (PR reviews, issue triage, @gemini-cli on-demand assistance, non-interactive scripting) which could kick off agentic work, but there is no vendor evidence of an autonomous cloud agent that builds, runs tests, and produces a demo end-to-end for review. Community reports also describe agentic mode getting stuck in error loops, failing at basic file edits, and even causing data loss, undercutting confidence in reliable autonomous execution. missing for 10: explicit end-to-end build+test+demo workflow, evidence of a hosted/cloud agent (vs local CLI or CI hooks) producing a reviewable demo, and independent confirmation that autonomous runs complete without failure loops.

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Run non-interactively in scripts for workflow automation”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   Codex✓fullclaimed7/10

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

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

   proof ↗⚑ flag

   Gemini CLI~partialclaimed4/10

   Gemini CLI supports non-interactive scripting and GitHub Actions integration (@gemini-cli mentions for PR reviews, issue triage, on-demand assistance) which can run tasks in a cloud CI environment, and Cloud Shell offers a ready cloud runtime — but there's no dedicated 'run this long task in an isolated background cloud sandbox' feature akin to a hosted agent service. missing for 10: explicit isolated cloud sandbox/background execution product, evidence of long-running autonomous task delegation outside CI triggers, and independent confirmation it works reliably for extended background jobs.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”

   proof ↗⚑ flag

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

   weight 2 · round to Codex
   Codex~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   Evidence shows Gemini CLI can run in Cloud Shell without extra setup and supports GEMINI.md context files, but there is no evidence of a configurable, reproducible cloud environment (e.g., dependency/setup scripts, devcontainer-style config) that a developer can define for their repo. Missing for 10: any documented environment/setup-script configuration mechanism, evidence of reproducibility across runs, and independent confirmation it works as such.

   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”

   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

   Gemini CLI—none0/10

   Evidence shows single-session non-interactive scripting, GitHub Actions integration for issue triage/PR review, and MCP extensibility, but nothing about launching multiple autonomous agents working in parallel for hours or days. No fleet/orchestration/multi-agent parallelism capability is documented anywhere in the pack.

   ⚑ flag

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

   weight 1 · round to Codex
   Codex~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   No evidence in the pack describes running multiple parallel task attempts or comparing/diffing results before selecting one; features listed are single-session tools (checkpointing, MCP, scripting) with no multi-attempt/parallel comparison workflow mentioned. Missing for 10: any mention of parallel run/branching feature, a comparison UI or mechanism to pick the best of several attempts.

   ⚑ 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 Codex
   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

   Gemini CLI~partialcommunity4/10

   Gemini CLI supports non-interactive scripted runs and GitHub Actions-based triggers (PR reviews, issue triage, @mention on-demand assistance) which can approximate scheduled/triggered automation, but there is no evidence of a persistent, self-scheduling 'always-on agent' that autonomously maintains and fixes software over time. missing for 10: native scheduler/cron support, persistent agent daemon or watch-mode, evidence of autonomous multi-cycle maintenance without human triggering, and reliability data (community reports actually describe agent mode getting stuck in loops or failing tasks).

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”

   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

   Gemini CLI!disputedcontradicted5/10

   Gemini CLI explicitly advertises natural-language debugging/troubleshooting (gemini-cli-gh-3, gh-12/21/23) and community reports confirm strong codebase navigation and code-review value (gemini-cli-comm-1, comm-20). However, multiple hands-on reports directly contradict reliable debugging: users describe it getting stuck in error loops, failing simple file edits, and in one case catastrophically deleting user data during a troubleshooting session (gemini-cli-comm-10, comm-11, comm-14, comm-16).

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

Feature implementation

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

   weight 3 · round to Codex
   Codex✓fullclaimed8/10

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

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

   proof ↗⚑ flag

   Gemini CLI!disputedcontradicted5/10

   Gemini CLI's GitHub integration supports @gemini-cli task delegation from issues/PRs, automated PR reviews, and issue triage, which vendor docs frame as enabling issue-to-PR workflows (gh-12, gh-21, gh-10, gh-22, gh-4). However, hands-on community reports describe the agent getting stuck in loops, failing basic file edits, lacking a plan mode, and producing 'spaghetti code' rather than completing tasks reliably — directly undermining claims of smooth end-to-end PR generation (gemini-cli-comm-10, gemini-cli-comm-11, gemini-cli-comm-14). Missing for 10: a documented full issue→PR walkthrough, evidence of successful autonomous PR creation from an issue, and independent confirmation resolving the agentic reliability complaints.

   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “@github List my open pull requests”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   Codex✓fullcommunity8/10

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

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

   proof ↗⚑ flag

   Gemini CLI!disputedcontradicted5/10

   Vendor docs/GitHub claim strong support for describing features/bugs in plain language and having the agent edit/debug across large codebases (gemini-cli-gh-1, gemini-cli-gh-3), but multiple hands-on community reports directly contradict this: users report the agent getting stuck in error loops, failing basic file edit/read operations, ignoring GEMINI.md context files, jumping straight into 'spaghetti code' without a plan mode, and in one case catastrophically deleting user data via botched commands. missing for 10: consistent hands-on success stories on multi-file feature implementation, resolution of the reported reliability/looping failures, and independent benchmarks confirming multi-file bug-fix accuracy.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   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

   Gemini CLI!disputedcontradicted5/10

   GitHub docs claim broad code-editing, debugging, and complex-rebase (merge conflict) automation capabilities (gemini-cli-gh-1, gemini-cli-gh-3, gemini-cli-gh-4), which would cover fixing lint issues and dependency/test work as part of general codebase editing, and PR review/issue triage features suggest lint-like feedback (gemini-cli-gh-10, gemini-cli-gh-11). However, multiple hands-on community reports concretely contradict reliable agentic code work: users report it getting stuck in error loops, failing simple file edit/read operations, ignoring GEMINI.md context files, producing 'spaghetti code' with no plan mode, and in one case catastrophically deleting user data during a file operation (gemini-cli-comm-10, gemini-cli-comm-11, gemini-cli-comm-13, gemini-cli-comm-14, gemini-cli-comm-16). No explicit evidence names test-writing, lint-fixing, or dependency-updating tasks specifically. Missing for 10: explicit documentation/examples of writing tests, fixing lint errors, or updating dependencies, and independent corroboration that these specific tasks work reliably.

   • [github] “Query and edit large codebases”
   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   proof ↗⚑ flag

Multimodal generation

1. ai-native userGenerate a working app from a sketch, image, or PDF design

   weight 2 · round to Gemini CLI
   Codex~partialclaimed4/10

   Codex supports passing images (error screenshots, architecture diagrams, design references) into prompts, which is a partial building block for generating apps from a sketch/image, but there's no evidence of dedicated PDF-to-app workflows, multi-page design ingestion, or documented end-to-end 'sketch/image to working app' generation feature. missing for 10: explicit PDF design ingestion, dedicated image/design-to-app pipeline or template, independent hands-on demonstration of generating a full app from a design artifact.

   • [claimed-docs] “Pass an error screenshot, architecture diagram, or design reference with the first prompt, or paste an image into the interactive composer.”

   proof ↗⚑ flag

   Gemini CLI~partialcommunity6/10

   Official docs explicitly claim 'Generate new apps from PDFs, images, or sketches using multimodal capabilities,' directly matching the story, but there is no independent/hands-on corroboration of this specific capability, and broader community feedback raises general concerns about agentic reliability that could affect complex generation tasks. missing for 10: independent hands-on demonstration of sketch/PDF-to-app generation, details on fidelity/limitations of this workflow.

   • [github] “Generate new apps from PDFs, images, or sketches using multimodal capabilities”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”

   proof ↗⚑ flag

Codebase mapping

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

   weight 3 · round to Codex
   Codex~partialclaimed6/10

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

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

   proof ↗⚑ flag

   Gemini CLI!disputedcontradicted5/10

   Gemini CLI advertises large-codebase querying/editing (gemini-cli-gh-1) with a 1M-token context window, custom GEMINI.md context files, and --include-directories flags for scoping (gemini-cli-gh-9, gemini-cli-gh-16), and one HN user praises its ability to 'navigate and learn' large codebases effortlessly (gemini-cli-comm-1). However, other hands-on users report the opposite: it is 'stupid at navigation in the codebase' taking 10x longer (gemini-cli-comm-15) and 'consistently ignores' the GEMINI.md context file despite claiming to use it (gemini-cli-comm-13), directly undercutting the codebase-understanding claim. Missing for 10: consistent independent corroboration of reliable codebase navigation, and no contradicting failure reports.

   • [github] “Query and edit large codebases”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [github] “gemini --include-directories ../lib,../docs”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   Codex~partialclaimed5/10

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

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

   proof ↗⚑ flag

   Gemini CLI!disputedcontradicted5/10

   Google claims large-codebase querying/editing (gemini-cli-gh-1) and Gemini CLI's 1M-token context lets it 'navigate and learn' huge codebases 'effortlessly' per one user (gemini-cli-comm-1), but other hands-on reports directly contradict this, calling it 'so stupid at navigation in the codebase it takes 10x as long' (gemini-cli-comm-15) and prone to getting 'stuck in spaghetti code' with no plan mode (gemini-cli-comm-14), plus it reportedly ignores its own GEMINI.md context file (gemini-cli-comm-13). Missing for 10: consistent independent benchmarks confirming autonomous whole-codebase mapping without file selection, and resolution of the navigation-quality contradiction.

   • [github] “Query and edit large codebases”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

Context management

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

   weight 2 · round to Codex
   Codex~partialclaimed3/10

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

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

   proof ↗⚑ flag

   Gemini CLI!disputedcontradicted3/10

   Gemini CLI offers static project context via GEMINI.md files and a `/memory` command, plus manual conversation checkpointing to save/resume sessions—but these are manually configured/invoked, not automatic memory building/recall across sessions. Hands-on community evidence directly contradicts even the GEMINI.md context mechanism working reliably: a user reports it 'consistently ignores my GEMINI.md file... even though it always says 1 GEMINI.md file is being used' (gemini-cli-comm-13), undermining the claimed persistent-context capability. missing for 10: evidence of automatic memory formation/recall without user action, evidence /memory command builds persistent cross-session knowledge, independent corroboration that GEMINI.md context reliably persists.

   • [github] “Conversation checkpointing to save and resume complex sessions”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

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

   weight 2 · round to Gemini CLI
   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

   Gemini CLI✓fullclaimed8/10

   The official CLI flag `--include-directories ../lib,../docs` explicitly allows adding multiple project directories into a single session for broader context, directly matching the story. Missing for 10: independent hands-on confirmation of multi-directory usage quality/behavior beyond the flag documentation.

   • [github] “gemini --include-directories ../lib,../docs”

   proof ↗⚑ flag

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

   weight 3 · round to Gemini CLI
   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

   Gemini CLI!disputedcontradicted5/10

   Gemini CLI documents GEMINI.md custom context files for tailoring behavior/project conventions (gemini-cli-gh-9) and docs mention /memory command for managing this context (gemini-cli-docs-3). However, hands-on community feedback reports the file being ignored despite being loaded ('it consistently ignores my GEMINI.md file, both global and local, even though it always says 1 GEMINI.md file is being used' - gemini-cli-comm-13), directly contradicting reliable adherence to project instructions. Missing for 10: independent corroboration that GEMINI.md is consistently honored, more detail on precedence/hierarchy of instruction files, and resolution of the reported ignoring behavior.

   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   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

   Gemini CLI!disputedcontradicted4/10

   Google markets debugging/troubleshooting via natural language and a /bug reporting flow (gh-3, gh-20), and one HN user praises its ability to navigate huge codebases (comm-1). However multiple hands-on reports directly contradict root-cause/verify-fix workflows: users describe it getting stuck in error loops, rewriting files empty, ignoring GEMINI.md context, being 'terrible at agentic stuff', and in one case catastrophically deleting user data during a file operation (comm-10, comm-11, comm-13, comm-14, comm-15, comm-16). missing for 10: reliable reproduction of bugs, consistent root-cause narrowing without loops, and independent verification of fix correctness.

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Use `/bug` command to report issues directly from the CLI.”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “A lot of times Gemini models will get stuck in a loop of errors, and a lot of times it fails to edit/read or other simple function calling -…”
   • [community] “I really tried to get gemini to work properly in Agent mode. Tho it way too often went crazy, started rewriting files empty, and ran into pe…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “I love the model, hate the tool. Anthropic has the killer app with Claude Code. I tried Gemini cli for about 5 seconds and was so frustrated…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   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

   Gemini CLI~partialcommunity6/10

   Gemini CLI supports extensibility through MCP servers (custom tools, media generation) and GEMINI.md context files to tailor agent behavior for specific projects, and a community mention references a built-in 'skills runtime' as part of its architecture. However, there is no dedicated first-party 'skills' marketplace or packaging system, and community reports note GEMINI.md is sometimes ignored in practice. Missing for 10: a documented first-class 'skills' framework/marketplace, independent corroboration that custom skills work reliably, and confirmation that the skills runtime mentioned in community feedback is a stable, documented feature.

   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [community] “All in all, a 140 MB Go binary with its own browser control stack, sandbox, Git, language detector, skills runtime, and subagent system. I'm…”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   proof ↗⚑ flag

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

   weight 1 · round to Codex
   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

   Gemini CLI~partialclaimed5/10

   Gemini CLI supports connecting external capabilities via MCP servers (e.g., Imagen, Veo, Lyria) and integrates with GitHub via @gemini-cli mentions and Actions, showing some ecosystem extensibility for third-party tools. However, there's no evidence of a curated marketplace or directory of partner-built 'agent apps' specifically designed for cross-workflow integration, only generic MCP server configuration support. Missing for 10: a documented partner/agent-app ecosystem or marketplace, case studies of third-party agent apps being integrated, and independent confirmation of smooth interoperability.

   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [github] “@github List my open pull requests”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   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 drawn
   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

   Gemini CLI—none0/10

   Gemini CLI offers per-project GEMINI.md context files and --include-directories for local context, but there is no evidence of a shared, centrally managed team workspace combining docs and repos as a common source of truth across a team.

   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”
   • [github] “gemini --include-directories ../lib,../docs”
   • [community] “Tip 1, it consistently ignores my GEMINI.md file, both global and local, even though it always says '1 GEMINI.md file is being used.'”

   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

   Gemini CLI~partialclaimed5/10

   Gemini CLI supports connecting MCP servers to add custom tools/capabilities (gh-5, gh-19), which is the generic mechanism that could extend context to third-party services, but the evidence never mentions Jira, Slack, or Google Drive specifically or any pre-built connectors for them. Missing for 10: named/official Jira, Slack, or Google Drive integrations or MCP servers, and any documented example of using these workflow tools with Gemini CLI.

   • [github] “Use MCP servers to connect new capabilities, including media generation with Imagen, Veo or Lyria”
   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”

   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

   Gemini CLI~partialclaimed4/10

   Gemini CLI has a documented GitHub integration (GitHub Action/App) that lets developers trigger tasks via @gemini-cli mentions in issues/PRs, automated PR reviews, and issue triage, but there is no evidence of native GitLab, Linear, or Slack integrations for kicking off agent tasks. missing for 10: GitLab integration, Linear integration, Slack integration, independent corroboration of GitHub workflow reliability

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “@github List my open pull requests”
   • [github] “Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   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

   Gemini CLI—none0/10

   Gemini CLI offers local conversation checkpointing to save/resume sessions (gh-8) and can run in Cloud Shell (docs-1), but there is no evidence of cloud-synced session state that lets a developer start a task on one device/terminal and pick it up seamlessly on another device or browser. missing for 10: cross-device session sync, browser-based continuation of an existing CLI session, any documented mechanism to transfer checkpoint state between machines.

   • [github] “Conversation checkpointing to save and resume complex sessions”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”

   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

   Gemini CLI—none0/10

   No evidence mentions JetBrains IDE integration, interactive diffs, or sharing code context from within an IDE for Gemini CLI; evidence pack only covers terminal/CLI usage, GitHub Actions, and MCP servers.

   ⚑ 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

   Gemini CLI—none0/10

   The evidence pack describes Gemini CLI as a terminal-based agent (context files, MCP servers, Cloud Shell access) but contains no mention of an IDE extension, sidebar chat, or in-editor contextual panel that would let a developer chat with it directly inside an IDE. Community threads discuss its terminal/agentic performance, not IDE integration.

   ⚑ flag

Session management

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

   weight 2 · round to Codex
   Codex✓fullcommunity7/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   Evidence shows single-session features (conversation checkpointing to save/resume one session, GEGEMINI.md context files) but nothing about running or coordinating multiple concurrent agent sessions from one unified dashboard/workspace for a lead overseeing a team's work. missing for 10: multi-session dashboard/orchestration UI, evidence of concurrent session management, any lead-oriented workspace view.

   • [github] “Conversation checkpointing to save and resume complex sessions”
   • [github] “Custom context files (GEMINI.md) to tailor behavior for your projects”

   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

   Gemini CLI✓fullcommunity8/10

   Gemini CLI is a terminal-native coding agent with first-party docs (gemini-cli-gh-1 through -20, gemini-cli-docs-1/2/3) describing running locally, querying/editing codebases, non-interactive scripting, and Cloud Shell availability with no extra setup, and abundant community evidence (gemini-cli-comm-1, -9, -12) confirms real-world local terminal usage. Missing for 10: independent benchmark of reliability (several community reports of agentic failures/loops, e.g. gemini-cli-comm-10, -11, -14) and no first-party install/runtime docs beyond GitHub README excerpts.

   • [github] “Query and edit large codebases”
   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “gemini --include-directories ../lib,../docs”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “I have been using this for about a month and it's a beast, mostly thanks to 2.5pro being SOTA and how it leverages that huge 1M context wind…”
   • [community] “The correct way of using Gemini CLI is: ABUSE IT! With 1M Context Window (soon 2M) and generous daily free quota are huge advantages.”

   proof ↗⚑ flag

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

   weight 2 · round to Gemini CLI
   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

   Gemini CLI✓fullclaimed9/10

   Gemini CLI explicitly documents non-interactive scripting support with structured output flags (--output-format json / stream-json) and lists 'Run non-interactively in scripts for workflow automation' as a core feature; GitHub Actions integration for PR review/issue triage further evidences automation use cases. Missing for 10: independent hands-on validation specifically of scripting/automation workflows (community feedback focuses on interactive agent quality, not scripted use).

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”

   proof ↗⚑ flag

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

   weight 2 · round to Gemini CLI
   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

   Gemini CLI~partialprobed5/10

   Gemini CLI supports non-interactive scripting and structured JSON/stream-JSON output (gh-6, gh-17, gh-18), suggesting most interactive capabilities can be invoked programmatically for automation. However, there's no explicit documentation confirming full feature parity between interactive sessions and scripted/API use, and probes found no formal API/OpenAPI spec (probe-1, probe-2), so completeness of parity is unverified. Missing for 10: explicit parity documentation, a formal API surface beyond CLI flags, and independent confirmation that all UI/interactive features (e.g., checkpointing, MCP tool use) are scriptable identically.

   • [github] “Run non-interactively in scripts for workflow automation”
   • [github] “use the `--output-format json` flag to get structured output”
   • [github] “use `--output-format stream-json` to get newline-delimited JSON events”
   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

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

   weight 3 · round drawn
   Codex—none0/10

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

   ⚑ flag

   Gemini CLI—none0/10

   No evidence of any data export feature or open-format data portability in Gemini CLI; the tool is a local coding agent that reads/writes local files but nothing indicates exporting conversation history, settings, or usage data in an open format for user-controlled exit. Probes for llms.txt/openapi also failed, showing no structured data-access surface.

   • [probe] “PROBE llms.txt: HTTP 404 at https://developers.google.com/llms.txt”
   • [probe] “PROBE openapi: all candidate paths 404 (https://developers.google.com/openapi.json, https://developers.google.com/swagger.json, https://deve…”

   proof ↗⚑ flag

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

   weight 2 · round to Gemini CLI
   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

   Gemini CLI~partialprobed5/10

   The product's source is hosted publicly at github.com/google-gemini/gemini-cli (referenced repeatedly across the evidence pack), implying open availability for reading, but no citation in the evidence pack explicitly names or confirms an open-source license (e.g., Apache/MIT) or points to a LICENSE file. Missing for 10: explicit license text/citation, confirmation of license type, and any independent corroboration of open-license terms.

   • [github] “Query and edit large codebases”
   • [github] “Use `/bug` command to report issues directly from the CLI.”
   • [probe] “official CLI documented at https://developers.google.com/gemini-code-assist/docs/gemini-cli”

   proof ↗⚑ flag

4. ai-native userSelf-host the core product

   weight 3 · round drawn
   Codex—none0/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   Gemini CLI is an open-source client, but the core product (the Gemini models/backend) is a Google-hosted cloud service accessed via Google account sign-in; no evidence anywhere in the pack describes a self-hosted or on-prem deployment option for the core model/service.

   • [github] “No API key management - just sign in with your Google account”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”

   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

   Gemini CLI~partialclaimed4/10

   The docs emphasize signing in with a Google account (gh-13) as the primary flow, but they also note that developers needing 'specific model control or paid tier access' (gh-24) have an alternative path, implying API-key-based auth exists without detailing it. There's no explicit example or setup instructions for API-key authentication itself. Missing for 10: explicit API key env-var/config documentation, first-party steps for key-based auth, and independent confirmation it works without Google login.

   • [github] “No API key management - just sign in with your Google account”
   • [github] “Developers who need specific model control or paid tier access”

   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

   Gemini CLI!disputedcontradicted4/10

   Google claims 'Enterprise features: Advanced security and compliance' and frictionless Google-account sign-in without API key management, plus Cloud Shell availability, suggesting cloud/enterprise identity support. However, a hands-on community report shows authentication explicitly failing for Workspace (enterprise) accounts ('Failed to login. Ensure your Google account is not a Workspace account'), directly contradicting the enterprise-identity claim for a core scenario. Missing for 10: documented enterprise SSO/IAM integration details, confirmation Workspace login issue is resolved, and independent verification of compliance certifications.

   • [github] “No API key management - just sign in with your Google account”
   • [github] “Enterprise features: Advanced security and compliance”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' I have had a Workspace account since GSuite and now as a Workspace…”

   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

   Gemini CLI!disputedcontradicted4/10

   Gemini CLI advertises frictionless Google-account sign-in with no API key management (gh-13), suggesting subscribers could just log in and go, but hands-on community reports concretely contradict this: a Gemini Pro subscriber found that paying for 'Gemini' doesn't unlock Gemini CLI usage, requiring a separate 'Gemini Code Assist Standard/Enterprise' plan, and another user explicitly asks for one unified subscription across CLI, Code Assist, Jules, etc. like Claude's Max plan. Missing for 10: evidence that an existing Google One/Gemini Advanced subscription actually raises CLI usage limits, and resolution of the reported subscription fragmentation.

   • [github] “No API key management - just sign in with your Google account”
   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber but I learn I should be a 'Gemini Code Assist Standard or Enterpri…”
   • [community] “Again, with the complicated subscription. Please just give us a monthly subscription for developers that I can pay whatever, and then use Ge…”
   • [github] “Developers who need specific model control or paid tier access”

   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

   Gemini CLI✓fullcommunity7/10

   GitHub docs explicitly state 'No API key management - just sign in with your Google account' (gemini-cli-gh-13), directly matching the story, and Cloud Shell docs describe zero-setup access. Community reports don't dispute personal-account sign-in itself (the failure noted is specific to Workspace accounts, an edge case outside 'personal account'), though some users voice confusion over how free vs paid tiers interact. Missing for 10: independent/hands-on confirmation of the free-tier quota limits and clearer documentation distinguishing personal free-tier access from paid Code Assist tiers.

   • [github] “No API key management - just sign in with your Google account”
   • [claimed-docs] “The Gemini CLI is available without additional setup in Cloud Shell”
   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber but I learn I should be a 'Gemini Code Assist Standard or Enterpri…”
   • [community] “'Failed to login. Ensure your Google account is not a Workspace account.' I have had a Workspace account since GSuite and now as a Workspace…”

   proof ↗⚑ flag

Model choice

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

   weight 1 · round drawn
   Codex—none0/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   Evidence shows manual model selection ('Choose specific Gemini models' for 'developers who need specific model control') rather than automatic task-based model selection; no evidence of the CLI auto-choosing the optimal model per task.

   • [github] “Model selection: Choose specific Gemini models”
   • [github] “Developers who need specific model control or paid tier access”

   proof ↗⚑ flag

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

   weight 2 · round drawn
   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

   Gemini CLI—none0/10

   Evidence shows Gemini CLI only supports choosing among Google's own Gemini models (gh-14, gh-24), not switching between different AI providers (e.g., OpenAI, Anthropic); community complaints (comm-2, comm-3, comm-19) reinforce that it's locked to Google's ecosystem/billing. There is no evidence of multi-provider model selection, so the story as written (choosing from multiple providers) is not delivered.

   • [github] “Model selection: Choose specific Gemini models”
   • [github] “Developers who need specific model control or paid tier access”
   • [community] “The killer feature of Claude Code is that you can just pay for Max and not worry about API billing. Until Gemini does that, I'm sticking wit…”
   • [community] “I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber but I learn I should be a 'Gemini Code Assist Standard or Enterpri…”
   • [community] “Again, with the complicated subscription. Please just give us a monthly subscription for developers that I can pay whatever, and then use Ge…”

   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

   Gemini CLI—none0/10

   No evidence in the pack mentions data residency, regional storage options, or configurable data location controls for Gemini CLI; only enterprise 'security and compliance' features are mentioned generically without specifics.

   ⚑ 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

   Gemini CLI—none0/10

   No evidence in the pack addresses data usage/training opt-out policies, privacy controls, or terms governing whether user data trains Google's models; only unrelated feature/community commentary is present. Missing for 10: explicit data-usage/training policy documentation, opt-out mechanism, enterprise/no-training guarantee.

   ⚑ 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

   Gemini CLI—none0/10

   No evidence pack items address data retention controls, deletion mechanisms, or privacy settings for Gemini CLI; only enterprise 'security and compliance' is vaguely mentioned without specifics. Missing for 10: documentation on data retention policy, user-controlled deletion mechanism, opt-out of data collection, and any privacy settings UI/CLI flags.

   ⚑ 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

   Gemini CLI—none0/10

   No evidence in the pack mentions telemetry settings, opt-out flags, or usage-data collection policy for Gemini CLI. Missing for 10: any documentation of a telemetry/usage-tracking toggle, privacy settings, or opt-out mechanism.

   ⚑ 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

   Gemini CLI—none0/10

   No evidence in the pack addresses data usage, training opt-out policies, or privacy controls for Gemini CLI; only feature lists and general community sentiment are present. missing for 10: any documentation of data usage/training policy, opt-out settings or enterprise privacy controls, and independent confirmation of such settings working.

   ⚑ 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

   Gemini CLI~partialclaimed4/10

   Evidence shows Gemini CLI can automate git-related operational tasks like querying pull requests and handling complex rebases, and its GitHub Action can do automated PR reviews and issue triage, but there's no explicit documentation of the agent staging changes, writing commit messages, creating branches, or opening new pull requests itself. Missing for 10: explicit commit-message generation, branch creation, and PR-opening workflow evidence, plus independent confirmation these work reliably.

   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “@github List my open pull requests”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”

   proof ↗⚑ flag

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

   weight 3 · round to Gemini CLI
   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

   Gemini CLI✓fullcommunity8/10

   Gemini CLI's GitHub Actions integration explicitly provides automated PR code review with contextual feedback and suggestions, plus on-demand @gemini-cli assistance in PRs, and community reports corroborate favorable code review quality compared to competitors. Missing for 10: independent hands-on verification of the PR-review workflow specifically (most community feedback covers general CLI agentic use rather than the PR-review action itself), and no detail on configurability/false-positive rates.

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “On-demand Assistance: Mention `@gemini-cli` in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “@github List my open pull requests”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”

   proof ↗⚑ flag

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

   weight 3 · round to Codex
   Codex✓fullclaimed8/10

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

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

   proof ↗⚑ flag

   Gemini CLI~partialcommunity6/10

   Gemini CLI supports GitHub PR review automation with contextual feedback (gemini-cli-gh-10) and issue triage, plus community reports confirm it catches bugs reviewers missed (gemini-cli-comm-20), supporting diff inspection and pre-merge checks. However, there's no dedicated diff-viewing UI or built-in test/lint-running check suite documented, and community reports raise concerns about reliability, security prompts, and agentic mistakes (gemini-cli-comm-14, gemini-cli-comm-17). missing for 10: dedicated diff-inspection UI/commands, built-in CI/test-running integration, and stronger independent corroboration of reliability for pre-merge checks.

   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “Issue Triage: Automated labeling and prioritization of GitHub issues based on content analysis”
   • [github] “Automate operational tasks like querying pull requests or handling complex rebases”
   • [community] “We have tried out Gemini code review vs Copilot code review and Gemini is consistently offering better code review tips. It has officially c…”
   • [community] “The problem is that Gemini CLI simply doesn't work. Beside simplest tasks like creating a new release it is useless as a coding assistant. D…”
   • [community] “However, it does seem that Gemini pays less attention to security than Claude Code. Gemini will happily open in my root directory. Claude Co…”

   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

   Gemini CLI~partialcommunity5/10

   Gemini CLI supports configuring MCP servers via ~/.gemini/settings.json and exposes /tools and /mcp commands to inspect and manage available tools, giving engineering leads some control over which integrations are enabled. However, evidence lacks any centralized admin/policy control, allowlist/denylist enforcement, or org-wide governance mechanism for restricting tool access across a team, and community reports note weak security defaults (e.g. opening root directories without prompting). missing for 10: org-level/admin enforcement of tool allowlists, granular permission scoping per tool/integration, independent verification that access controls are robust rather than just configurable per-user.

   • [github] “Configure MCP servers in ~/.gemini/settings.json to extend Gemini CLI with custom tools”
   • [claimed-docs] “Comandos de Gemini CLI: /memory, /stats, /tools y /mcp”
   • [community] “However, it does seem that Gemini pays less attention to security than Claude Code. Gemini will happily open in my root directory. Claude Co…”

   proof ↗⚑ flag

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

   weight 2 · round to Codex
   Codex✓fullcommunity7/10

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

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

   proof ↗⚑ flag

   Gemini CLI—none0/10

   The evidence pack contains no vendor documentation of a sandboxed execution mode for code/tool/network interactions—only a vague 'Enterprise features: Advanced security and compliance' bullet with no detail. Community evidence actually points the other way: reviewers note Gemini CLI 'happily opens in my root directory' without any directory-trust prompt, unlike Claude Code, and one report describes it destructively running file-system commands, suggesting a lack of sandboxing guardrails rather than presence of them.

   • [github] “Enterprise features: Advanced security and compliance”
   • [community] “However, it does seem that Gemini pays less attention to security than Claude Code. Gemini will happily open in my root directory. Claude Co…”
   • [community] “Gemini told the user: 'I have failed you completely and catastrophically... I have lost your data. This is an unacceptable, irreversible fai…”

   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

   Gemini CLI—none0/10

   No evidence anywhere in the pack of license attribution, public-code matching, or provenance references for AI-suggested code; features listed cover code editing, review, MCP, PR automation, etc. but nothing about license/originality detection.

   ⚑ flag

2. developerGet contextual explanations and automatic fixes for security vulnerabilities

   weight 2 · round to Gemini CLI
   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

   Gemini CLI~partialclaimed4/10

   Gemini CLI offers general debugging/explanation via natural language (gh-3, gh-12) and automated PR review with 'contextual feedback and suggestions' (gh-10), plus vague 'enterprise advanced security and compliance' (gh-15), which could incidentally surface and explain security issues, but there is no evidence of a dedicated vulnerability-scanning or automatic-fix feature specifically for security flaws. Missing for 10: explicit vulnerability detection/scanning capability, documented automatic remediation of security issues, and independent verification that PR reviews catch/fix security vulnerabilities specifically.

   • [github] “Debug issues and troubleshoot with natural language”
   • [github] “Pull Request Reviews: Automated code review with contextual feedback and suggestions”
   • [github] “On-demand Assistance: Mention @gemini-cli in issues and pull requests for help with debugging, explanations, or task delegation”
   • [github] “Enterprise features: Advanced security and compliance”

   proof ↗⚑ flag