Agent skill

Codex Guide

by K9i-0 in K9i-0/ccpocket

Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は codex execpolicy check で実検証すること。

MITAuto-check passedAgent Workflows

Install Codex Guide

skills CLI
$ npx skills add K9i-0/ccpocket --skill codex-guide -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install K9i-0/ccpocket codex-guide --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/K9i-0/ccpocket.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/codex-guide .claude/skills/codex-guide && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codex-guide
GitHub stars
1.1k
Token cost
~475 tokens
SKILL.md length
158 words
Files
2 (incl. references)
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は codex execpolicy check で実検証すること。

  • Works in 3 steps: まず公式 docs を探す → rules / execpolicy の相談なら必ず検証する → 実運用に近いコマンドで再確認する
  • Tasks that involve Subagents
  • SKILL.md covers この skill を使う場面, 基本方針, 標準ワークフロー and 特に注意すること, plus 2 more sections
  • Calls codex

What it does

Codex Guide is an agent skill from K9i-0/ccpocket. Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は codex execpolicy check で実検証すること。

Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/official-sources.md`).

It sits in Agent Workflows, covering Subagents and Agent instruction files. It works with OpenAI. The repository describes itself as: Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge. The licence is MIT.

When your agent uses it

  • Tasks that involve Subagents
  • Tasks that involve Agent instruction files

Example prompts

  • “/codex-guide”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. まず公式 docs を探す
  2. rules / execpolicy の相談なら必ず検証する
  3. 実運用に近いコマンドで再確認する

What it can do on your machine

Read from SKILL.md and the folder at commit 8354ffd. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • codex

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codex Guide loads about 475 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 45 tokens; SKILL.md has 158 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~475
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from K9i-0/ccpocket at commit 8354ffd, republished under its MIT licence (© K9i-0). 158 words, ~475 tokens.

Download SKILL.mdSave it as .claude/skills/codex-guide/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
codex-guide
description
Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は `codex execpolicy check` で実検証すること。

Codex Guide

Codex の使い方や仕様を案内するときのガイド。

この skill を使う場面

  • ユーザーが Codex CLI / app / IDE extension の使い方を聞いたとき
  • rules, execpolicy, approvals, hooks, AGENTS.md, skills, subagents, MCP, config を説明するとき
  • Codex のモデル、設定、コマンド、slash command、運用方法を案内するとき
  • Codex について「本当にそういう仕様か」を確認したいとき

基本方針

  • 記憶で断定しない。 まず OpenAI の公式 Codex docs を確認する。
  • 仕様説明は一次情報優先。 非公式ブログや推測をベースにしない。
  • rules / approvals は docs だけで終わらせない。 codex execpolicy check で実際の判定を確認する。
  • コマンド挙動は再現確認する。 可能なら軽い実コマンドで allow / prompt / forbidden を確かめる。
  • 変わりやすい情報は公式 docs hub から辿る。 直リンクが変わっていそうなら Codex docs トップから探し直す。

標準ワークフロー

1. まず公式 docs を探す

用途ごとに references/official-sources.md の該当ページを開く。

  • Codex 全体像: docs hub / CLI / Academy
  • 設定: Config basics / advanced / reference / sample
  • approvals / rules: Rules
  • カスタマイズ: Skills / Subagents / AGENTS.md / Hooks / MCP
  • 実践例: Academy / Use cases / openai/codex
2. rules / execpolicy の相談なら必ず検証する

変更提案前に、少なくとも以下を実行する。

bash
codex execpolicy check --pretty --rules <rules-file> -- <command...>

最低 2 パターン確認すること。

  • 許可したいコマンド
  • 止めたい、または prompt にしたいコマンド

部分許可を設計するときは、重なる rule も確認する。

3. 実運用に近いコマンドで再確認する

execpolicy check だけでなく、可能なら軽い実コマンドでも確認する。

例:

  • allow 想定の軽いコマンドを 1 本
  • prompt 想定の軽いコマンドを 1 本

特に注意すること

  • prefix_rule は複数一致する。最終判定は より厳しい decision が勝つ。
  • 部分 allow を書いても、より広い prompt が同時一致すると最終的に prompt になる。
  • 迷ったら「広く allow、危ないサブコマンドだけ prompt」か、「全部明示列挙」のどちらかで設計する。
  • match / not_match を書ける場面では書く。意図ミスの早期発見に使う。

返答のしかた

  • 公式 docs を見てわかったことと、ローカルで検証したことを分けて書く。
  • 推測が混じる場合は、それが推測だと明示する。
  • ルール提案時は、提案内容だけでなく「なぜその rule が最終判定になるか」も書く。

参照先

詳細な URL と用途は references/official-sources.md を見る。

© K9i-0, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .claude/skills/codex-guide of K9i-0/ccpocket.

  • SKILL.md
  • references/official-sources.md

Open the folder on GitHubat commit 8354ffd

Compare with similar skills

Codex Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codex Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codex Guide this skillK9i-0/ccpocket1.1k—~475Automated safety check: PassMIT
Prime Agentwcygan/dotfiles196—~1.8kAutomated safety check: PassNone
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0
Harness Agent Team Designerrevfactory/harness9.1k—~4.5kAutomated safety check: PassApache-2.0
Repo Task Proof LoopDenisSergeevitch/repo-task-proof-loop730—~3.8kAutomated safety check: PassApache-2.0
Rules Distillationaffaan-m/ECC274k2 repos~2.3kAutomated safety check: PassMIT

Similar skills

  • Prime Agent

    wcygan/dotfiles

    A skill your agent uses when learning, configuring, or troubleshooting Prime Agent (PrimeIntellect-ai/prime-agent), including installation, providers, custom OpenAI-compatible models, local…

    196 GitHub stars~1.8k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed
  • Harness Agent Team Designer

    revfactory/harness

    Designs a project-specific agent harness: defines specialist agents, writes the skills they follow, picks an execution mode and model for each, and keeps the setup maintained.

    9.1k GitHub stars~4.5k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed
  • Repo Task Proof Loop

    DenisSergeevitch/repo-task-proof-loop

    Repo-local workflow skill for large coding tasks. An agent skill from DenisSergeevitch/repo-task-proof-loop.

    730 GitHub stars~3.8k tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check passed
  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    274k GitHub starsUsed in 2 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Remember Learnings

    dyad-sh/dyad

    Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.

    22k GitHub stars~1.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from K9i-0/ccpocket

All 17 skills in this repo
  • Sim Preview

    K9i-0/ccpocket

    iOSシミュレーターで動くFlutterアプリをExpo Device HubとTailscale HTTPSでスマホのブラウザへ配信・操作するときに使う。

    1.1k GitHub stars~711 tokensUpdated 4 days ago
    Auto-check passed
  • Submit Store Review

    K9i-0/ccpocket

    既存の安定ビルドをApp Store / Google Playの審査へ提出・再提出する。新規ビルドはrelease-appを使う。

    1.1k GitHub stars~1.8k tokensUpdated 4 days ago
    Auto-check passed
  • Web Preview

    K9i-0/ccpocket

    Flutter Web版をビルドしてユーザーにプレビューURLを案内する。playwright-cliでアクセス確認も行う。

    1.1k GitHub stars~359 tokensUpdated 4 days ago
    Auto-check passed
  • Flutter UI Design

    K9i-0/ccpocket

    Flutter UI実装のアーキテクチャ規約・コンポーネント分割・状態管理ガイド(Bloc/Cubit版). An agent skill from K9i-0/ccpocket.

    1.1k GitHub stars~1.2k tokensUpdated 4 days ago
    Auto-check passed
  • Flutter Upgrade

    K9i-0/ccpocket

    Flutter SDKのアップグレード、または指定バージョンへの移行影響を調査するときに使う. An agent skill from K9i-0/ccpocket.

    1.1k GitHub stars~789 tokensUpdated 4 days ago
    Auto-check passed
  • Release App

    K9i-0/ccpocket

    ccpocketアプリのバージョン更新と、指定プラットフォーム向けリリースを行う. An agent skill from K9i-0/ccpocket.

    1.1k GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed

Works with

Categories

Questions about Codex Guide

What does Codex Guide do?

Codex の使い方、CLI/app/IDE、rules・hooks・AGENTS.md・skills・subagents・config などを案内する。Codex や OpenAI 製品の仕様を答える前に必ず公式ドキュメントを確認し、rules/approval は codex execpolicy check で実検証すること。. Codex Guide is an agent skill from K9i-0/ccpocket.

When should I use Codex Guide?

Codex Guide fits situations like: tasks that involve Subagents; tasks that involve Agent instruction files.

How do I install Codex Guide in Claude Code?

Run `npx skills add K9i-0/ccpocket --skill codex-guide -a claude-code`. Or copy the skill folder (.claude/skills/codex-guide in K9i-0/ccpocket) into .claude/skills/codex-guide in your project. Claude Code loads it when a task matches its description.

How do I install Codex Guide in Codex?

Run `npx skills add K9i-0/ccpocket --skill codex-guide -a codex`. Or copy the skill folder (.claude/skills/codex-guide in K9i-0/ccpocket) into .agents/skills/codex-guide in your project. Codex loads it when a task matches its description.

Can I use Codex Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add K9i-0/ccpocket --skill codex-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-guide, .gemini/skills/codex-guide, .github/skills/codex-guide and .opencode/skills/codex-guide in your project.

What does Codex Guide need to run?

Going by SKILL.md and its folder, Codex Guide needs the command-line tools its instructions call (codex).

Does Codex Guide access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Codex Guide safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Codex Guide use?

Codex Guide is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codex Guide use?

About 475 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 774 tokens, read only when the agent opens those files.

What are the alternatives to Codex Guide?

Skills that share tags, products or a category with Codex Guide: Prime Agent (wcygan/dotfiles, 196 stars), Task Observer (rebelytics/one-skill-to-rule-them-all, 3.2k stars), Harness Agent Team Designer (revfactory/harness, 9.1k stars) and Repo Task Proof Loop (DenisSergeevitch/repo-task-proof-loop, 730 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codex Guide?

K9i-0 (a GitHub user) maintains it in K9i-0/ccpocket, which has 1,082 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 3, 2026.

Source: K9i-0/ccpocket on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.