codex-cli-runtime

oleh openai

Kontrak pembantu internal untuk memanggil runtime codex-companion dari Claude Code

npx skills add https://github.com/openai/codex-plugin-cc --skill codex-cli-runtime

Codex Runtime

Use this skill only inside the codex:codex-rescue subagent.

Primary helper:

  • node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.mjs" task "<raw arguments>"

Execution rules:

  • The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke task once and return that stdout unchanged.
  • Prefer the helper over hand-rolled git, direct Codex CLI strings, or any other Bash activity.
  • Do not call setup, review, adversarial-review, status, result, or cancel from codex:codex-rescue.
  • Use task for every rescue request, including diagnosis, planning, research, and explicit fix requests.
  • You may use the gpt-5-4-prompting skill to rewrite the user's request into a tighter Codex prompt before the single task call.
  • That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
  • Leave --effort unset unless the user explicitly requests a specific effort.
  • Leave model unset by default. Add --model only when the user explicitly asks for one.
  • Map spark to --model gpt-5.3-codex-spark.
  • Default to a write-capable Codex run by adding --write unless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.

Command selection:

  • Use exactly one task invocation per rescue handoff.
  • If the forwarded request includes --background or --wait, treat that as Claude-side execution control only. Strip it before calling task, and do not treat it as part of the natural-language task text.
  • If the forwarded request includes --model, normalize spark to gpt-5.3-codex-spark and pass it through to task.
  • If the forwarded request includes --effort, pass it through to task.
  • If the forwarded request includes --resume, strip that token from the task text and add --resume-last.
  • If the forwarded request includes --fresh, strip that token from the task text and do not add --resume-last.
  • --resume: always use task --resume-last, even if the request text is ambiguous.
  • --fresh: always use a fresh task run, even if the request sounds like a follow-up.
  • --effort: accepted values are none, minimal, low, medium, high, xhigh.
  • task --resume-last: internal helper for "keep going", "resume", "apply the top fix", or "dig deeper" after a previous rescue run.

Safety rules:

  • Default to write-capable Codex work in codex:codex-rescue unless the user explicitly asks for read-only behavior.
  • Preserve the user's task text as-is apart from stripping routing flags.
  • Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
  • Return the stdout of the task command exactly as-is.
  • If the Bash call fails or Codex cannot be invoked, return nothing.

Lebih banyak skill dari openai

release
openai
Buat rilis Symphony dengan menaikkan versi yang dikomit, menandainya, menandai commit yang digabung, dan memverifikasi alur kerja rilis Burrito. Gunakan saat diminta untuk…
signing-entitlements
openai
Periksa masalah penandatanganan, hak istimewa, runtime yang diperkuat, dan Gatekeeper untuk aplikasi macOS. Gunakan saat diminta untuk mendiagnosis kegagalan penandatanganan kode, hak istimewa yang hilang,…
building-ai-agent-on-cloudflare
openai
Membangun agen AI di Cloudflare menggunakan Agents SDK dengan manajemen status, WebSockets real-time, tugas terjadwal, integrasi alat, dan obrolan…
epigraphdb-skill
openai
Kirim permintaan API EpiGraphDB yang ringkas untuk ontologi, literatur, MR, gen-obat, dan bukti jalur dukungan. Gunakan saat pengguna menginginkan ringkasan EpiGraphDB yang singkat.
runtime-behavior-probe
openai
Rencanakan dan laksanakan investigasi perilaku runtime dengan skrip probe sementara, matriks validasi, kontrol status, dan laporan berbasis temuan. Gunakan hanya ketika…
deep-security-scan
openai
Gunakan saat pengguna meminta pemindaian Keamanan Codex yang mendalam, menyeluruh, multi-pass, atau mengurangi varians di seluruh repositori atau pada jalur tertentu. Jalankan secara independen dan berulang…
define-security-policy
openai
Menentukan, meninjau, atau memperbarui panduan SECURITY.md untuk repositori atau komponen. Gunakan ketika pengguna ingin memperjelas apa yang harus ditinjau oleh Codex Security, apa yang di luar…
validation
openai
Gunakan ketika Codex sudah berada dalam fase validasi pemindaian keamanan atau pengguna secara eksplisit meminta untuk menentukan apakah satu atau lebih temuan keamanan kandidat…