菜单
Codex CLI sub-agent for dispatching tasks to OpenAI-compatible models via the `codex` binary. Use for code-focused tasks routed to GPT-5 Codex or any OpenAI-compatible endpoint. Part of the run_agent.py multi-LLM task router — cli=codex target.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/richfrem/agent-plugins-skills --skill codex-cli-agent命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Scaffolds a new top-level agent plugin directory. NOT for scaffolding single skills (use `create-skill`) and NOT for adding MCP integrations to existing plugins (use `create-mcp-integration`).
This skill should be used when the user wants to "create a marketplace", "setup a marketplace catalog", "scaffold marketplace.json", "initialize a plugin registry", or "configure a Gemini CLI extension". Use this even if they just mention "setting up a marketplace".
Cooperative Multi-Agent Coordination Loop. Spawns a lightweight companion sub-agent (Gemini 3.5 Flash Low) to perform spec discovery, planning, and implementation. The primary agent (Claude) acts as the QA Director, answering Gemini's questions, approving the spec/plan, and running verification tests. Assumes the superpowers plugin is installed in the target repository.
基于 SOC 职业分类
正在显示 SKILL.md
| name | codex-cli-agent |
| plugin | cli-agents |
| description | Codex CLI sub-agent for dispatching tasks to OpenAI-compatible models via the `codex` binary. Use for code-focused tasks routed to GPT-5 Codex or any OpenAI-compatible endpoint. Part of the run_agent.py multi-LLM task router — cli=codex target. |
| allowed-tools | Bash, Read, Write |
Dispatches bounded tasks to the Codex CLI (codex binary). Uses the run_agent.py task router with cli=codex.
[!IMPORTANT] Default model:
gpt-5-codex. RequiresOPENAI_API_KEYin environment. Thecodexbinary must be on PATH.
run_agent.pypython ./scripts/run_agent.py \
<PERSONA_FILE> <INPUT_FILE> <OUTPUT_FILE> "<INSTRUCTION>" \
--cli codex --model gpt-5-codex
The prompt is piped to codex exec via stdin — not passed as a positional arg — to avoid OS ARG_MAX limits and process listing exposure.
python ./scripts/run_agent.py \
agents/refactor-expert.md \
target.py \
refactor.md \
"Refactor this function and explain the top 3 changes." \
--cli codex
python ./scripts/run_agent.py \
agents/security-auditor.md \
target.py \
security.md \
"Find vulnerabilities. Rate severity: CRITICAL / MODERATE / MINOR." \
--cli codex --model gpt-4o
| Use Case | Why codex |
|---|---|
| Code review / refactor | GPT-5 Codex is code-optimized |
| OpenAI endpoint routing | Use any OPENAI_BASE_URL-compatible target |
| Isolated sub-task to GPT-5 | No main agent context bleed |
agents/)| Persona | Use For |
|---|---|
security-auditor.md | Red team, vulnerability scanning |
refactor-expert.md | Code optimization, DRY, readability |
architect-review.md | System design, modularity |
echo "Say hello in one sentence." | codex exec --model gpt-5-codex -
python ./scripts/run_agent.py agents/refactor-expert.md target.py output.md "Summarize this file." --cli codex
echo $OPENAI_API_KEY # must be set
which codex # must be on PATH
codex --version
codex exec --help # verify exec subcommand and available flags