返回列表

codex

v1.0.6

Use Codex from Claude Code to review code or delegate tasks.

安装命令

先运行 claude 启动会话,再在会话内执行下列斜杠命令。
安装技能
›/plugin install codex@datou-market
添加市场源首次使用需要 · 已添加过可跳过
直连(GitHub)
›/plugin marketplace add https://github.com/Garretqaq/plugins-market
首次使用先「添加市场源」,之后安装本市场的其它技能无需重复添加。国内访问 GitHub 慢时,用「代理加速」地址。

技能说明

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.

文件结构

plugin.json
CHANGELOG.md
LICENSE
NOTICE
codex-rescue.md
adversarial-review.md
cancel.md
rescue.md
result.md
review.md
setup.md
status.md
transfer.md
hooks.json
adversarial-review.md
stop-review-gate.md
review-output.schema.json
app-server-broker.mjs
codex-companion.mjs
app-server-protocol.d.ts
app-server.mjs
args.mjs
broker-endpoint.mjs
broker-lifecycle.mjs
claude-session-transfer.mjs
codex.mjs
fs.mjs
git.mjs
job-control.mjs
process.mjs
prompts.mjs
render.mjs
state.mjs
tracked-jobs.mjs
workspace.mjs
session-lifecycle-hook.mjs
stop-review-gate-hook.mjs
SKILL.md
SKILL.md
SKILL.md
codex-prompt-antipatterns.md
codex-prompt-recipes.md
prompt-blocks.md