[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77MJGDTRXGEE4FETDSXCTCX":3,"skill-same:01M77MJGDTRXGEE4FETDSXCTCX":57},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M77MJGDTRXGEE4FETDSXCTCX","codex-subagent",null,"Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). Use when delegating a self-contained coding task to Codex from another agent — parallel implementation work, a second opinion, or an independent verification pass.","davidondrej\u002Fskills","davidondrej","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F131768515?v=4","01M77MHARFKYVNT9FV22807T8F","David Ondrej","01M77MHASHNDV507F9NTVKR2CY",4310,"MIT","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcodex-subagent\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codex-subagent\ndescription: Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key). Use when delegating a self-contained coding task to Codex from another agent — parallel implementation work, a second opinion, or an independent verification pass.\ndisable-model-invocation: true\ntriggers: [user, model]\n---\n\n# Codex CLI as a Subagent\n\nCodex CLI is OpenAI's terminal coding agent. `codex exec` runs it non-interactively:\nit works autonomously in a sandbox, streams progress to stderr, and prints only the\nfinal message to stdout. Auth reuses the user's ChatGPT subscription — never an API key.\n\n## When to delegate\n\n- Self-contained coding task with clear success criteria (fix, feature, refactor, review).\n- Parallel work: several independent tasks at once (see Parallel runs).\n- Second opinion \u002F independent verification of your own changes.\n\nDo NOT delegate tasks that need conversation context you can't fully write into the prompt.\n\n## Preflight\n\n```bash\ncodex --version       # missing? npm i -g @openai\u002Fcodex  (or: brew install --cask codex)\ncodex login status    # exit 0 + \"Logged in using ChatGPT\" = ready\n```\n\nNot logged in → stop and tell the user to run `codex login` (one-time browser OAuth).\nNever read, print, or copy credentials (`~\u002F.codex\u002Fauth.json`).\n\n## Launch\n\n```bash\nOUT=$(mktemp \u002Ftmp\u002Fcodex-out.XXXXXX)\ncodex exec \\\n  --cd \u002Fpath\u002Fto\u002Frepo \\\n  --model gpt-5.6-sol \\\n  --config model_reasoning_effort=high \\\n  --sandbox workspace-write \\\n  --output-last-message \"$OUT\" \\\n  \"Full task prompt: goal, constraints, files to touch, definition of done.\" \\\n  \u003C\u002Fdev\u002Fnull\n```\n\n- Always use GPT 5.6 Sol (`gpt-5.6-sol`). Default reasoning effort to `high`.\n  Pass both flags explicitly on every new Codex run.\n- Do NOT use Codex fast mode.\n- `\u003C\u002Fdev\u002Fnull` is MANDATORY when stdin is not a real terminal (background shells,\n  scripts): codex treats open stdin as extra context and waits forever for EOF.\n- Codex sees NOTHING of your conversation. Put all context in the prompt:\n  goal, relevant paths, constraints, and how to verify it's done.\n- Long prompt? Pipe it via stdin instead: `codex exec [flags] - \u003C \u002Ftmp\u002Ftask.md`.\n- Wrap the command in a background\u002FBash subagent if your host agent has one\n  (Cursor: Task tool with a shell subagent) so Codex's verbose stream stays out\n  of the parent context. Fallback: a plain background terminal.\n- Runs take minutes and have no built-in timeout — background it and monitor.\n- Optional: `--json` for JSONL event stream.\n\n## Collect results\n\n```bash\ncat \"$OUT\"                            # final message = the deliverable\ngit -C \u002Fpath\u002Fto\u002Frepo status --short   # see what Codex actually changed\n```\n\nFollow-up in the same session (run from the same cwd — resume filters by cwd):\n\n```bash\ncodex exec resume --last \"follow-up instruction\" \u003C\u002Fdev\u002Fnull\n```\n\n## Parallel runs\n\nParallelize only genuinely independent tasks, and assign file ownership upfront so\nresults merge cleanly. One git worktree per Codex run — never two in the same tree:\n\n```bash\ngit worktree add \u002Ftmp\u002Fwt-taskA -b codex\u002Ftask-a\ncodex exec --cd \u002Ftmp\u002Fwt-taskA --model gpt-5.6-sol \\\n  --config model_reasoning_effort=high --sandbox workspace-write \\\n  -o \u002Ftmp\u002FoutA.md \"task A\" \u003C\u002Fdev\u002Fnull\n```\n\n## Failure modes\n\n- Hangs forever with no output → stdin was left open. Kill it, relaunch with `\u003C\u002Fdev\u002Fnull`.\n- `codex login status` non-zero → the user must run `codex login`. Don't work around it.\n- ChatGPT plan rate limit hit → report to the user; never retry in a loop.\n- \"Not a git repo\" error → add `--skip-git-repo-check`, or init a repo first.\n- Network is blocked inside the workspace-write sandbox by default. If the task\n  needs it (installs, API calls): `-c sandbox_workspace_write.network_access=true`.\n- NEVER use `--dangerously-bypass-approvals-and-sandbox`.\n\n## Rules\n\n- One task per launch. Split big jobs into multiple launches.\n- Review Codex's diff yourself before declaring the task done.\n\n## Cursor-native wrapper (optional)\n\nFor auto-routing and `\u002Fcodex` invocation inside Cursor, add `~\u002F.cursor\u002Fagents\u002Fcodex.md` —\na custom subagent whose description is \"delegates coding tasks to Codex CLI\" and whose\nbody points at this skill.\n","# Codex CLI as a Subagent\n\nCodex CLI is OpenAI's terminal coding agent. `codex exec` runs it non-interactively:\nit works autonomously in a sandbox, streams progress to stderr, and prints only the\nfinal message to stdout. Auth reuses the user's ChatGPT subscription — never an API key.\n\n## When to delegate\n\n- Self-contained coding task with clear success criteria (fix, feature, refactor, review).\n- Parallel work: several independent tasks at once (see Parallel runs).\n- Second opinion \u002F independent verification of your own changes.\n\nDo NOT delegate tasks that need conversation context you can't fully write into the prompt.\n\n## Preflight\n\n```bash\ncodex --version       # missing? npm i -g @openai\u002Fcodex  (or: brew install --cask codex)\ncodex login status    # exit 0 + \"Logged in using ChatGPT\" = ready\n```\n\nNot logged in → stop and tell the user to run `codex login` (one-time browser OAuth).\nNever read, print, or copy credentials (`~\u002F.codex\u002Fauth.json`).\n\n## Launch\n\n```bash\nOUT=$(mktemp \u002Ftmp\u002Fcodex-out.XXXXXX)\ncodex exec \\\n  --cd \u002Fpath\u002Fto\u002Frepo \\\n  --model gpt-5.6-sol \\\n  --config model_reasoning_effort=high \\\n  --sandbox workspace-write \\\n  --output-last-message \"$OUT\" \\\n  \"Full task prompt: goal, constraints, files to touch, definition of done.\" \\\n  \u003C\u002Fdev\u002Fnull\n```\n\n- Always use GPT 5.6 Sol (`gpt-5.6-sol`). Default reasoning effort to `high`.\n  Pass both flags explicitly on every new Codex run.\n- Do NOT use Codex fast mode.\n- `\u003C\u002Fdev\u002Fnull` is MANDATORY when stdin is not a real terminal (background shells,\n  scripts): codex treats open stdin as extra context and waits forever for EOF.\n- Codex sees NOTHING of your conversation. Put all context in the prompt:\n  goal, relevant paths, constraints, and how to verify it's done.\n- Long prompt? Pipe it via stdin instead: `codex exec [flags] - \u003C \u002Ftmp\u002Ftask.md`.\n- Wrap the command in a background\u002FBash subagent if your host agent has one\n  (Cursor: Task tool with a shell subagent) so Codex's verbose stream stays out\n  of the parent context. Fallback: a plain background terminal.\n- Runs take minutes and have no built-in timeout — background it and monitor.\n- Optional: `--json` for JSONL event stream.\n\n## Collect results\n\n```bash\ncat \"$OUT\"                            # final message = the deliverable\ngit -C \u002Fpath\u002Fto\u002Frepo status --short   # see what Codex actually changed\n```\n\nFollow-up in the same session (run from the same cwd — resume filters by cwd):\n\n```bash\ncodex exec resume --last \"follow-up instruction\" \u003C\u002Fdev\u002Fnull\n```\n\n## Parallel runs\n\nParallelize only genuinely independent tasks, and assign file ownership upfront so\nresults merge cleanly. One git worktree per Codex run — never two in the same tree:\n\n```bash\ngit worktree add \u002Ftmp\u002Fwt-taskA -b codex\u002Ftask-a\ncodex exec --cd \u002Ftmp\u002Fwt-taskA --model gpt-5.6-sol \\\n  --config model_reasoning_effort=high --sandbox workspace-write \\\n  -o \u002Ftmp\u002FoutA.md \"task A\" \u003C\u002Fdev\u002Fnull\n```\n\n## Failure modes\n\n- Hangs forever with no output → stdin was left open. Kill it, relaunch with `\u003C\u002Fdev\u002Fnull`.\n- `codex login status` non-zero → the user must run `codex login`. Don't work around it.\n- ChatGPT plan rate limit hit → report to the user; never retry in a loop.\n- \"Not a git repo\" error → add `--skip-git-repo-check`, or init a repo first.\n- Network is blocked inside the workspace-write sandbox by default. If the task\n  needs it (installs, API calls): `-c sandbox_workspace_write.network_access=true`.\n- NEVER use `--dangerously-bypass-approvals-and-sandbox`.\n\n## Rules\n\n- One task per launch. Split big jobs into multiple launches.\n- Review Codex's diff yourself before declaring the task done.\n\n## Cursor-native wrapper (optional)\n\nFor auto-routing and `\u002Fcodex` invocation inside Cursor, add `~\u002F.cursor\u002Fagents\u002Fcodex.md` —\na custom subagent whose description is \"delegates coding tasks to Codex CLI\" and whose\nbody points at this skill.\n",{"name":5,"triggers":24,"description":7,"disable-model-invocation":27},[25,26],"user","model",true,"main","a9d4ad810cf3c303fde23bdcd5fc86df7c57daf3","skills\u002Fcodex-subagent",626,"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills","https:\u002F\u002Fwww.cloudroom.dev","https:\u002F\u002Fgithub.com\u002Fdavidondrej","https:\u002F\u002Fwww.cloudroom.dev\u002F","founder of Cloudroom","2026-11-14 10:00:36",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":27},[40,43,46],{"tool":41,"command":42},"npx","npx skills add davidondrej\u002Fskills --skill codex-subagent",{"tool":44,"command":45},"bunx","bunx skills add davidondrej\u002Fskills --skill codex-subagent",{"tool":47,"command":48},"pnpm","pnpm dlx skills add davidondrej\u002Fskills --skill codex-subagent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcodex-subagent\u002FSKILL.md",[51],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"agents\u002Fopenai.yaml","REFERENCE","参考文档",43,"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcodex-subagent\u002Fagents\u002Fopenai.yaml",[58,65,72,79,86,93],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M77MPMR6DE13EZFSMY76S6YB","varied-search","Research a topic across the web, GitHub, and X\u002FTwitter with DeepAPI and produce a concise Markdown report. Use for varied-search or requests to compare web coverage, relevant repositories, and social discussion.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvaried-search\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M77MPG5F9H2JBW4VFHBY1VSM","total-review","Run five independent max-effort reviews (Fable 5.1, Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Muse Wonder), merge their findings, and fix only what the user approves. Use for \u002Ftotal-review, or when the user or another agent asks for a total review.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftotal-review\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M77MP8XZJ42ZJZQV8C76B353","stop-overthinking","Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstop-overthinking\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M77MP5EGQSNF1VS9SY8CK60Q","state","Manually-invoked skill that recaps what the current thread is doing and how far along it is. Use when the user says \"state\", \"where are we\", or \"what % are we done\".","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fstate\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M77MP2H479SWAP7687RAVG7T","setup-help","Guide setup one step at a time and show what remains. Use only when the user explicitly asks for it by name.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fsetup-help\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M77MNZV9X8NPC9JZMWP8WAF8","self-archive","Archive the current Cloudroom thread and release its runtime. Use only when the user explicitly asks to self-archive, archive yourself, or archive this thread.","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fself-archive\u002FSKILL.md",[],[]]