{"id":"edbbd08e-e7bf-4171-a9f0-dfad82b7615f","shortId":"p64LF5","kind":"skill","title":"codex","tagline":"Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing","description":"# Codex Skill Guide\n\n## Running a Task\n1. Ask the user (via `AskUserQuestion`) which model to run (`gpt-5.2-codex` or `gpt-5.2`) AND which reasoning effort to use (`xhigh`, `high`, `medium`, or `low`) in a **single prompt with two questions**.\n2. Select the sandbox mode required for the task; default to `--sandbox read-only` unless edits or network access are necessary.\n3. Assemble the command with the appropriate options:\n   - `-m, --model <MODEL>`\n   - `--config model_reasoning_effort=\"<xhigh|high|medium|low>\"`\n   - `--sandbox <read-only|workspace-write|danger-full-access>`\n   - `--full-auto`\n   - `-C, --cd <DIR>`\n   - `--skip-git-repo-check`\n3. Always use --skip-git-repo-check.\n4. When continuing a previous session, use `codex exec --skip-git-repo-check resume --last` via stdin. When resuming don't use any configuration flags unless explicitly requested by the user e.g. if he species the model or the reasoning effort when requesting to resume a session. Resume syntax: `echo \"your prompt here\" | codex exec --skip-git-repo-check resume --last 2>/dev/null`. All flags have to be inserted between exec and resume.\n5. **IMPORTANT**: By default, append `2>/dev/null` to all `codex exec` commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed.\n6. Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.\n7. **After Codex completes**, inform the user: \"You can resume this Codex session at any time by saying 'codex resume' or asking me to continue with additional analysis or changes.\"\n\n### Quick Reference\n| Use case | Sandbox mode | Key flags |\n| --- | --- | --- |\n| Read-only review or analysis | `read-only` | `--sandbox read-only 2>/dev/null` |\n| Apply local edits | `workspace-write` | `--sandbox workspace-write --full-auto 2>/dev/null` |\n| Permit network or broad access | `danger-full-access` | `--sandbox danger-full-access --full-auto 2>/dev/null` |\n| Resume recent session | Inherited from original | `echo \"prompt\" \\| codex exec --skip-git-repo-check resume --last 2>/dev/null` (no flags allowed) |\n| Run from another directory | Match task needs | `-C <DIR>` plus other flags `2>/dev/null` |\n\n## Following Up\n- After every `codex` command, immediately use `AskUserQuestion` to confirm next steps, collect clarifications, or decide whether to resume with `codex exec resume --last`.\n- When resuming, pipe the new prompt via stdin: `echo \"new prompt\" | codex exec resume --last 2>/dev/null`. The resumed session automatically uses the same model, reasoning effort, and sandbox mode from the original session.\n- Restate the chosen model, reasoning effort, and sandbox mode when proposing follow-up actions.\n\n## Error Handling\n- Stop and report failures whenever `codex --version` or a `codex exec` command exits non-zero; request direction before retrying.\n- Before you use high-impact flags (`--full-auto`, `--sandbox danger-full-access`, `--skip-git-repo-check`) ask the user for permission using AskUserQuestion unless it was already given.\n- When output includes warnings or partial results, summarize them and ask how to adjust using `AskUserQuestion`.","tags":["codex","claude","arsenal","majiayu000","agent-skills","ai-agents","ai-coding-assistant","automation","claude-code","code-review","developer-tools","devops"],"capabilities":["skill","source-majiayu000","skill-codex","topic-agent-skills","topic-ai-agents","topic-ai-coding-assistant","topic-automation","topic-claude","topic-claude-code","topic-code-review","topic-developer-tools","topic-devops","topic-productivity","topic-prompt-engineering","topic-python"],"categories":["claude-arsenal"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/majiayu000/claude-arsenal/codex","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add majiayu000/claude-arsenal","source_repo":"https://github.com/majiayu000/claude-arsenal","install_from":"skills.sh"}},"qualityScore":"0.464","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 29 github stars · SKILL.md body (3,219 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-01T07:01:13.170Z","embedding":null,"createdAt":"2026-04-18T22:24:04.720Z","updatedAt":"2026-05-01T07:01:13.170Z","lastSeenAt":"2026-05-01T07:01:13.170Z","tsv":"'-5.2':43,47 '/dev/null':199,216,312,327,346,365,381,423 '1':32 '2':66,198,215,311,326,345,364,380,422 '3':88,127 '4':135 '5':210 '6':244 '7':260 'access':85,116,332,336,341,492 'action':455 'addit':286 'adjust':523 'allow':368 'alreadi':508 'alway':128 'analysi':21,287,303 'anoth':371 'append':214 'appli':313 'appropri':94,252 'ask':6,33,281,498,520 'askuserquest':37,390,504,525 'assembl':89 'auto':119,325,344,487 'autom':24 'automat':427 'broad':331 'c':120,376 'captur':248 'case':293 'cd':121 'chang':289 'check':126,134,148,195,361,497 'chosen':443 'clarif':396 'cli':10 'code':20 'codex':1,9,11,13,18,26,44,142,189,219,262,271,278,355,386,403,418,463,467 'collect':395 'command':91,221,247,387,469 'complet':263 'config':98 'configur':159 'confirm':392 'continu':137,284 'danger':114,334,339,490 'danger-full-access':113,333,338,489 'debug':241 'decid':398 'default':75,213 'direct':475 'directori':372 'e.g':167 'echo':185,353,415 'edit':25,82,315 'effort':51,101,176,433,446 'error':456 'everi':385 'exec':12,143,190,207,220,356,404,419,468 'exit':470 'explicit':162,233 'failur':461 'filter':250 'flag':160,201,297,367,379,484 'follow':382,453 'follow-up':452 'full':115,118,324,335,340,343,486,491 'full-auto':117,323,342,485 'git':124,132,146,193,359,495 'given':509 'gpt':42,46 'guid':28 'handl':457 'high':55,103,482 'high-impact':481 'immedi':388 'impact':483 'import':211 'includ':512 'inform':264 'inherit':350 'insert':205 'key':296 'last':150,197,363,406,421 'local':314 'low':58,105 'm':96 'match':373 'medium':56,104 'mode':70,295,436,449 'model':39,97,99,172,431,444 'necessari':87 'need':243,375 'network':84,329 'new':411,416 'next':393 'non':472 'non-zero':471 'openai':17 'option':95 'origin':352,439 'outcom':256 'output':511 'partial':515 'permiss':502 'permit':328 'pipe':409 'plus':377 'previous':139 'prompt':62,187,354,412,417 'propos':451 'question':65 'quick':290 'read':79,108,299,305,309 'read-on':78,107,298,304,308 'reason':50,100,175,432,445 'recent':348 'refactor':22 'refer':16,291 'repo':125,133,147,194,360,496 'report':460 'request':163,178,234,474 'requir':71 'restat':441 'result':516 'resum':14,149,154,180,183,196,209,269,279,347,362,401,405,408,420,425 'retri':477 'review':301 'run':8,29,41,245,369 'sandbox':69,77,106,294,307,319,337,435,448,488 'say':277 'see':236 'select':67 'session':140,182,272,349,426,440 'show':228 'singl':61 'skill':27 'skill-codex' 'skip':123,131,145,192,358,494 'skip-git-repo-check':122,130,144,191,357,493 'source-majiayu000' 'speci':170 'stderr':226,229 'stdin':152,414 'stdout/stderr':249 'step':394 'stop':458 'summar':254,517 'suppress':223 'syntax':184 'task':31,74,374 'think':224,237 'time':275 'token':225,238 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding-assistant' 'topic-automation' 'topic-claude' 'topic-claude-code' 'topic-code-review' 'topic-developer-tools' 'topic-devops' 'topic-productivity' 'topic-prompt-engineering' 'topic-python' 'two':64 'unless':81,161,505 'use':2,53,129,141,157,292,389,428,480,503,524 'user':5,35,166,232,259,266,500 'version':464 'via':36,151,413 'warn':513 'whenev':462 'whether':399 'workspac':111,317,321 'workspace-writ':110,316,320 'write':112,318,322 'xhigh':54,102 'zero':473","prices":[{"id":"1896e5a5-3320-4e38-8eee-b592724cd977","listingId":"edbbd08e-e7bf-4171-a9f0-dfad82b7615f","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"majiayu000","category":"claude-arsenal","install_from":"skills.sh"},"createdAt":"2026-04-18T22:24:04.720Z"}],"sources":[{"listingId":"edbbd08e-e7bf-4171-a9f0-dfad82b7615f","source":"github","sourceId":"majiayu000/claude-arsenal/codex","sourceUrl":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/codex","isPrimary":false,"firstSeenAt":"2026-04-18T22:24:04.720Z","lastSeenAt":"2026-05-01T07:01:13.170Z"}],"details":{"listingId":"edbbd08e-e7bf-4171-a9f0-dfad82b7615f","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"majiayu000","slug":"codex","github":{"repo":"majiayu000/claude-arsenal","stars":29,"topics":["agent-skills","ai-agents","ai-coding-assistant","automation","claude","claude-code","code-review","developer-tools","devops","productivity","prompt-engineering","python","software-development","typescript","workflows"],"license":"mit","html_url":"https://github.com/majiayu000/claude-arsenal","pushed_at":"2026-04-29T04:12:22Z","description":"52 production-ready Claude Code skills and 7 specialized agents for software development, DevOps, product workflows, and automation.","skill_md_sha":"a559d2c1ee772211fc62b9b6813bc2fdf43039f8","skill_md_path":"skills/codex/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/majiayu000/claude-arsenal/tree/main/skills/codex"},"layout":"multi","source":"github","category":"claude-arsenal","frontmatter":{"name":"codex","description":"Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing"},"skills_sh_url":"https://skills.sh/majiayu000/claude-arsenal/codex"},"updatedAt":"2026-05-01T07:01:13.170Z"}}