[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AV1RQSC4YYRHTFR2SRDXY4":3,"skill-same:01M7AV1RQSC4YYRHTFR2SRDXY4":62},{"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":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M7AV1RQSC4YYRHTFR2SRDXY4","codex",null,"Delegate coding to OpenAI Codex CLI (features, PRs).","peterlau123\u002Fskills-you-need","peterlau123","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F19188200?v=4","01M7AV0Y55C30Y4E2TGRQ8X7WR","Sloth","01M7AV0Y5SNAJQ4E3FG1EEK8S4",0,"MIT","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fautonomous-ai-agents\u002Fcodex\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codex\ndescription: \"Delegate coding to OpenAI Codex CLI (features, PRs).\"\nversion: 1.0.1\nauthor: Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    tags: [Coding-Agent, Codex, OpenAI, Code-Review, Refactoring]\n    related_skills: [claude-code, hermes-agent]\n---\n\n# Codex CLI\n\nDelegate coding tasks to [Codex](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex) via the Hermes terminal. Codex is OpenAI's autonomous coding agent CLI.\n\n## When to use\n\n- Building features\n- Refactoring\n- PR reviews\n- Batch issue fixing\n\nRequires the codex CLI and a git repository.\n\n## Prerequisites\n\n- Codex installed: `npm install -g @openai\u002Fcodex`\n- OpenAI auth configured: either `OPENAI_API_KEY` or Codex OAuth credentials\n  from the Codex CLI login flow\n- **Must run inside a git repository** — Codex refuses to run outside one\n- Use `pty=true` in terminal calls — Codex is an interactive terminal app\n\nFor Hermes itself, `model.provider: openai-codex` uses Hermes-managed Codex\nOAuth from `~\u002F.hermes\u002Fauth.json` after `hermes auth add openai-codex`. For the\nstandalone Codex CLI, a valid CLI OAuth session may live under\n`~\u002F.codex\u002Fauth.json`; do not treat a missing `OPENAI_API_KEY` alone as proof\nthat Codex auth is missing.\n\n## One-Shot Tasks\n\n```\nterminal(command=\"codex exec 'Add dark mode toggle to settings'\", workdir=\"~\u002Fproject\", pty=true)\n```\n\nFor scratch work (Codex needs a git repo):\n```\nterminal(command=\"cd $(mktemp -d) && git init && codex exec 'Build a snake game in Python'\", pty=true)\n```\n\n## Background Mode (Long Tasks)\n\n```\n# Start in background with PTY\nterminal(command=\"codex exec --sandbox workspace-write 'Refactor the auth module'\", workdir=\"~\u002Fproject\", background=true, pty=true)\n# Returns session_id\n\n# Monitor progress\nprocess(action=\"poll\", session_id=\"\u003Cid>\")\nprocess(action=\"log\", session_id=\"\u003Cid>\")\n\n# Send input if Codex asks a question\nprocess(action=\"submit\", session_id=\"\u003Cid>\", data=\"yes\")\n\n# Kill if needed\nprocess(action=\"kill\", session_id=\"\u003Cid>\")\n```\n\n## Key Flags\n\n| Flag | Effect |\n|------|--------|\n| `exec \"prompt\"` | One-shot execution, exits when done |\n| `--sandbox workspace-write` (`-s`) | Sandboxed but auto-approves file changes in the workspace (the recommended auto-build mode) |\n| `--dangerously-bypass-approvals-and-sandbox` | No sandbox, no approvals (fastest, most dangerous; `--yolo` still works as a hidden alias) |\n| `--sandbox danger-full-access` | No Codex sandbox; useful when the host service context breaks bubblewrap |\n\n> **Deprecated:** `--full-auto` still works but the live CLI warns to use `--sandbox workspace-write` instead.\n\n## Hermes Gateway Caveat\n\nWhen invoking the Codex CLI from a Hermes gateway\u002Fservice context (for example,\nTelegram-driven agent sessions), Codex `workspace-write` sandboxing may fail even\nwhen the same command works in the user's interactive shell. A typical symptom is\nbubblewrap\u002Fuser-namespace errors such as `setting up uid map: Permission denied`\nor `loopback: Failed RTM_NEWADDR: Operation not permitted`.\n\nIn that context, prefer:\n\n```\ncodex exec --sandbox danger-full-access \"\u003Ctask>\"\n```\n\nUse process boundaries as the safety layer instead: explicit `workdir`, clean git\nstatus before launch, narrow task prompts, `git diff` review, targeted tests, and\nhuman\u002Fagent confirmation before committing broad changes.\n\n## PR Reviews\n\nClone to a temp directory for safe review:\n\n```\nterminal(command=\"REVIEW=$(mktemp -d) && git clone https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo.git $REVIEW && cd $REVIEW && gh pr checkout 42 && codex review --base origin\u002Fmain\", pty=true)\n```\n\n## Parallel Issue Fixing with Worktrees\n\n```\n# Create worktrees\nterminal(command=\"git worktree add -b fix\u002Fissue-78 \u002Ftmp\u002Fissue-78 main\", workdir=\"~\u002Fproject\")\nterminal(command=\"git worktree add -b fix\u002Fissue-99 \u002Ftmp\u002Fissue-99 main\", workdir=\"~\u002Fproject\")\n\n# Launch Codex in each\nterminal(command=\"codex --sandbox workspace-write exec 'Fix issue #78: \u003Cdescription>. Commit when done.'\", workdir=\"\u002Ftmp\u002Fissue-78\", background=true, pty=true)\nterminal(command=\"codex --sandbox workspace-write exec 'Fix issue #99: \u003Cdescription>. Commit when done.'\", workdir=\"\u002Ftmp\u002Fissue-99\", background=true, pty=true)\n\n# Monitor\nprocess(action=\"list\")\n\n# After completion, push and create PRs\nterminal(command=\"cd \u002Ftmp\u002Fissue-78 && git push -u origin fix\u002Fissue-78\")\nterminal(command=\"gh pr create --repo user\u002Frepo --head fix\u002Fissue-78 --title 'fix: ...' --body '...'\")\n\n# Cleanup\nterminal(command=\"git worktree remove \u002Ftmp\u002Fissue-78\", workdir=\"~\u002Fproject\")\n```\n\n## Batch PR Reviews\n\n```\n# Fetch all PR refs\nterminal(command=\"git fetch origin '+refs\u002Fpull\u002F*\u002Fhead:refs\u002Fremotes\u002Forigin\u002Fpr\u002F*'\", workdir=\"~\u002Fproject\")\n\n# Review multiple PRs in parallel\nterminal(command=\"codex exec 'Review PR #86. git diff origin\u002Fmain...origin\u002Fpr\u002F86'\", workdir=\"~\u002Fproject\", background=true, pty=true)\nterminal(command=\"codex exec 'Review PR #87. git diff origin\u002Fmain...origin\u002Fpr\u002F87'\", workdir=\"~\u002Fproject\", background=true, pty=true)\n\n# Post results\nterminal(command=\"gh pr comment 86 --body '\u003Creview>'\", workdir=\"~\u002Fproject\")\n```\n\n## Rules\n\n1. **Always use `pty=true`** — Codex is an interactive terminal app and hangs without a PTY\n2. **Git repo required** — Codex won't run outside a git directory. Use `mktemp -d && git init` for scratch\n3. **Use `exec` for one-shots** — `codex exec \"prompt\"` runs and exits cleanly\n4. **`--sandbox workspace-write` for building** — auto-approves changes within the sandbox (`--full-auto` is deprecated for this)\n5. **Background for long tasks** — use `background=true` and monitor with `process` tool\n6. **Don't interfere** — monitor with `poll`\u002F`log`, be patient with long-running tasks\n7. **Parallel is fine** — run multiple Codex processes at once for batch work\n","# Codex CLI\n\nDelegate coding tasks to [Codex](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex) via the Hermes terminal. Codex is OpenAI's autonomous coding agent CLI.\n\n## When to use\n\n- Building features\n- Refactoring\n- PR reviews\n- Batch issue fixing\n\nRequires the codex CLI and a git repository.\n\n## Prerequisites\n\n- Codex installed: `npm install -g @openai\u002Fcodex`\n- OpenAI auth configured: either `OPENAI_API_KEY` or Codex OAuth credentials\n  from the Codex CLI login flow\n- **Must run inside a git repository** — Codex refuses to run outside one\n- Use `pty=true` in terminal calls — Codex is an interactive terminal app\n\nFor Hermes itself, `model.provider: openai-codex` uses Hermes-managed Codex\nOAuth from `~\u002F.hermes\u002Fauth.json` after `hermes auth add openai-codex`. For the\nstandalone Codex CLI, a valid CLI OAuth session may live under\n`~\u002F.codex\u002Fauth.json`; do not treat a missing `OPENAI_API_KEY` alone as proof\nthat Codex auth is missing.\n\n## One-Shot Tasks\n\n```\nterminal(command=\"codex exec 'Add dark mode toggle to settings'\", workdir=\"~\u002Fproject\", pty=true)\n```\n\nFor scratch work (Codex needs a git repo):\n```\nterminal(command=\"cd $(mktemp -d) && git init && codex exec 'Build a snake game in Python'\", pty=true)\n```\n\n## Background Mode (Long Tasks)\n\n```\n# Start in background with PTY\nterminal(command=\"codex exec --sandbox workspace-write 'Refactor the auth module'\", workdir=\"~\u002Fproject\", background=true, pty=true)\n# Returns session_id\n\n# Monitor progress\nprocess(action=\"poll\", session_id=\"\u003Cid>\")\nprocess(action=\"log\", session_id=\"\u003Cid>\")\n\n# Send input if Codex asks a question\nprocess(action=\"submit\", session_id=\"\u003Cid>\", data=\"yes\")\n\n# Kill if needed\nprocess(action=\"kill\", session_id=\"\u003Cid>\")\n```\n\n## Key Flags\n\n| Flag | Effect |\n|------|--------|\n| `exec \"prompt\"` | One-shot execution, exits when done |\n| `--sandbox workspace-write` (`-s`) | Sandboxed but auto-approves file changes in the workspace (the recommended auto-build mode) |\n| `--dangerously-bypass-approvals-and-sandbox` | No sandbox, no approvals (fastest, most dangerous; `--yolo` still works as a hidden alias) |\n| `--sandbox danger-full-access` | No Codex sandbox; useful when the host service context breaks bubblewrap |\n\n> **Deprecated:** `--full-auto` still works but the live CLI warns to use `--sandbox workspace-write` instead.\n\n## Hermes Gateway Caveat\n\nWhen invoking the Codex CLI from a Hermes gateway\u002Fservice context (for example,\nTelegram-driven agent sessions), Codex `workspace-write` sandboxing may fail even\nwhen the same command works in the user's interactive shell. A typical symptom is\nbubblewrap\u002Fuser-namespace errors such as `setting up uid map: Permission denied`\nor `loopback: Failed RTM_NEWADDR: Operation not permitted`.\n\nIn that context, prefer:\n\n```\ncodex exec --sandbox danger-full-access \"\u003Ctask>\"\n```\n\nUse process boundaries as the safety layer instead: explicit `workdir`, clean git\nstatus before launch, narrow task prompts, `git diff` review, targeted tests, and\nhuman\u002Fagent confirmation before committing broad changes.\n\n## PR Reviews\n\nClone to a temp directory for safe review:\n\n```\nterminal(command=\"REVIEW=$(mktemp -d) && git clone https:\u002F\u002Fgithub.com\u002Fuser\u002Frepo.git $REVIEW && cd $REVIEW && gh pr checkout 42 && codex review --base origin\u002Fmain\", pty=true)\n```\n\n## Parallel Issue Fixing with Worktrees\n\n```\n# Create worktrees\nterminal(command=\"git worktree add -b fix\u002Fissue-78 \u002Ftmp\u002Fissue-78 main\", workdir=\"~\u002Fproject\")\nterminal(command=\"git worktree add -b fix\u002Fissue-99 \u002Ftmp\u002Fissue-99 main\", workdir=\"~\u002Fproject\")\n\n# Launch Codex in each\nterminal(command=\"codex --sandbox workspace-write exec 'Fix issue #78: \u003Cdescription>. Commit when done.'\", workdir=\"\u002Ftmp\u002Fissue-78\", background=true, pty=true)\nterminal(command=\"codex --sandbox workspace-write exec 'Fix issue #99: \u003Cdescription>. Commit when done.'\", workdir=\"\u002Ftmp\u002Fissue-99\", background=true, pty=true)\n\n# Monitor\nprocess(action=\"list\")\n\n# After completion, push and create PRs\nterminal(command=\"cd \u002Ftmp\u002Fissue-78 && git push -u origin fix\u002Fissue-78\")\nterminal(command=\"gh pr create --repo user\u002Frepo --head fix\u002Fissue-78 --title 'fix: ...' --body '...'\")\n\n# Cleanup\nterminal(command=\"git worktree remove \u002Ftmp\u002Fissue-78\", workdir=\"~\u002Fproject\")\n```\n\n## Batch PR Reviews\n\n```\n# Fetch all PR refs\nterminal(command=\"git fetch origin '+refs\u002Fpull\u002F*\u002Fhead:refs\u002Fremotes\u002Forigin\u002Fpr\u002F*'\", workdir=\"~\u002Fproject\")\n\n# Review multiple PRs in parallel\nterminal(command=\"codex exec 'Review PR #86. git diff origin\u002Fmain...origin\u002Fpr\u002F86'\", workdir=\"~\u002Fproject\", background=true, pty=true)\nterminal(command=\"codex exec 'Review PR #87. git diff origin\u002Fmain...origin\u002Fpr\u002F87'\", workdir=\"~\u002Fproject\", background=true, pty=true)\n\n# Post results\nterminal(command=\"gh pr comment 86 --body '\u003Creview>'\", workdir=\"~\u002Fproject\")\n```\n\n## Rules\n\n1. **Always use `pty=true`** — Codex is an interactive terminal app and hangs without a PTY\n2. **Git repo required** — Codex won't run outside a git directory. Use `mktemp -d && git init` for scratch\n3. **Use `exec` for one-shots** — `codex exec \"prompt\"` runs and exits cleanly\n4. **`--sandbox workspace-write` for building** — auto-approves changes within the sandbox (`--full-auto` is deprecated for this)\n5. **Background for long tasks** — use `background=true` and monitor with `process` tool\n6. **Don't interfere** — monitor with `poll`\u002F`log`, be patient with long-running tasks\n7. **Parallel is fine** — run multiple Codex processes at once for batch work\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":37,"description":7},"Hermes Agent","1.0.1",{"hermes":27},{"tags":28,"related_skills":34},[29,30,31,32,33],"Coding-Agent","Codex","OpenAI","Code-Review","Refactoring",[35,36],"claude-code","hermes-agent",[38,39,40],"linux","macos","windows","main","c0b220603dea88e986e5b31268098ef2f5b07fd0","autonomous-ai-agents\u002Fcodex","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need","https:\u002F\u002Fgithub.com\u002Fpeterlau123","A software engineer in deep learning\r\n","2026-08-19 16:46:00",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add peterlau123\u002Fskills-you-need --skill codex",{"tool":54,"command":55},"bunx","bunx skills add peterlau123\u002Fskills-you-need --skill codex",{"tool":57,"command":58},"pnpm","pnpm dlx skills add peterlau123\u002Fskills-you-need --skill codex","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fautonomous-ai-agents\u002Fcodex\u002FSKILL.md",true,[],[63,70,77,84,91,98],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7AVH2D16QBRC8T2P6SVXSTS","jekyll-chirpy-blog","Use when editing the Jekyll\u002FChirpy blog or fixing mermaid.","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fweb\u002Fjekyll-chirpy-blog\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7AVGYYFDK4GKCSNHBCP59Y6","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fsoftware-development\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7AVGT9GAVB5EBKZ2616R27Z","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fsystematic-debugging\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7AVGQ23T5EHRQP5GZ45KZC5","spike","Throwaway experiments to validate an idea before build.","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fspike\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7AVGKZ0ZD91ATKD9QB44E1B","simplify-code","Parallel 4-agent cleanup of recent code changes.","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fsoftware-development\u002Fsimplify-code\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7AVGFBR76BWQNG2X4CN5SQT","requesting-code-review","Pre-commit review: security scan, quality gates, auto-fix.","https:\u002F\u002Fgithub.com\u002Fpeterlau123\u002Fskills-you-need\u002Fblob\u002Fmain\u002Fsoftware-development\u002Frequesting-code-review\u002FSKILL.md",[],[]]