菜单
Use for current official documentation about Codex, Codex CLI, or Claude Code behavior, configuration, prompting, skills, permissions, tools, surfaces, capabilities, troubleshooting, hooks, app-server, or hook trust; fetch the relevant official URL before answering.
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/PaulRBerg/agent-skills --skill agents-docs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。
正在显示 SKILL.md
| compatibility | Requires network access and a URL-capable web fetch or curl. |
| coordination | exempt |
| disable-model-invocation | false |
| name | agents-docs |
| user-invocable | true |
| description | Use for current official documentation about Codex, Codex CLI, or Claude Code behavior, configuration, prompting, skills, permissions, tools, surfaces, capabilities, troubleshooting, hooks, app-server, or hook trust; fetch the relevant official URL before answering. |
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
Before doing any work, identify the current chat host. If it is not Claude Code or Codex CLI, stop with this error:
This skill only works in Claude Code or Codex CLI.
Answer Codex and Claude Code product questions from the narrowest relevant live official documentation.
Classify the request as Codex, Claude Code, or a comparison. Activate only for questions about those products and their documented behavior. Do not capture unrelated repository mentions, generic agent development, provider APIs, SDKs, pricing, authentication, model selection, migration, or managed-agent workflows.
https://developers.openai.com. Start broad product research at
https://developers.openai.com/codex/codex-manual.md.https://code.claude.com. Start broad product research at
https://code.claude.com/docs/en/overview.md.rg, and read only the matching heading range into context. Do not write it or a cache into the repository or skill
installation.curl -fsSL.Follow redirects only within the matching official domain and cite the final page URL.
When a Codex feature or config.toml key is missing from the prose documentation, use this bounded procedure:
codex --version and codex features list.config-schema.json to an operating-system temporary location, then search only the relevant
definition or path. Do not cache the schema in the repository or skill installation.codex --strict-config --help; use one-off -c
overrides when needed without persisting changes. Parsing acceptance is not runtime proof.Do not turn this into a full feature inventory: investigate only the key or feature relevant to the request.
For Codex hooks, app-server, managed hooks, or hook-trust operations, first fetch the relevant official pages:
https://developers.openai.com/codex/hookshttps://developers.openai.com/codex/app-serverThen read the version-aware hooks reference. Use its local protocol and config details only when the installed client is explicitly verified as the version named there. Keep official behavior and local observations distinct in the answer; do not turn a local implementation detail into a product guarantee.
If retrieval fails, try the direct URL and one domain-restricted search, then stop expanding sources. State the bounded
uncertainty. Use local --help, --version, configuration, or observed behavior only when relevant and label it as
local evidence. Never silently substitute third-party sources, another provider's docs, or bundled knowledge.
For comparisons, answer a supported side even if the other provider is unavailable; mark the unsupported side unknown instead of manufacturing symmetry. In network-disabled sessions, fail transparently without creating repository files or persistent caches.
Finish when the answer uses the narrowest relevant official source, includes precise citations, and exposes any documentation/local-version discrepancy or retrieval limitation.
Assess recurrence risk for agent behavior using local Codex/Claude Code transcripts and recommend evidence-backed durable fixes to AGENTS.md or skills. Not for routine post-success skill-evolution or agent self-improvement reviews.
Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, installed project skills, and other Markdown context docs.
Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved plan.