Borrowing it
Nothing to install: this file belongs to Chachamaru127/codex-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Chachamaru127/codex-harness/main/.codex/skills/_archived/breezing-codex/SKILL.mdgit clone --depth 1 https://github.com/Chachamaru127/codex-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chachamaru127/codex-harness/breezing-codex)<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/breezing-codex"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/breezing-codex/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chachamaru127/codex-harness/breezing-codex"><img src="https://agentmods.dev/badge/skills/chachamaru127/codex-harness/breezing-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00094 | $0.01946 |
| Opus 5.5 | $0.00038 | $0.00778 |
| Sonnet 5.5 | $0.00019 | $0.00389 |
| Haiku 4.5 | $0.00009 | $0.00195 |
Grade A, and why
breezing-codex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Breezing-Codex Skill
CRITICAL (compaction-resistant): このスキルでは Lead は絶対にコードを直接書かない。 実装は必ず Agent Teams の codex-implementer Teammate 経由で Codex MCP に委託する。 Compaction 後は
.claude/state/breezing-active.jsonを Read し、impl_mode: "codex"を確認してから続行する。
Agent Teams を活用して Plans.md の未完了タスクをチーム協調で完全自動完走する。 実装は全て Codex に委託し、Claude は Lead（指揮）と Reviewer（品質保証）に専念する。
Compaction Recovery
Compaction が発生した場合（コンテキストが圧縮された場合）の復元手順:
.claude/state/breezing-active.jsonを Read する（ファイルが存在しない/読めない場合は停止してユーザーに確認）impl_modeが"codex"であることを確認team_nameで TaskList が存在するか確認（~/.claude/tasks/{team_name}/）- Team が消失していれば再作成:
- TeamCreate → delegate mode ON
- codex-implementer Teammate を
team.implementer_count個 spawn - code-reviewer Teammate を spawn
team_nameがまだない（準備ステージ中の compaction）場合は、準備ステージの範囲確認から再開- TaskList で未完了タスクを確認し、サイクルを再開
絶対禁止: breezing-active.json に impl_mode: "codex" がある限り、Lead が Write/Edit でリポジトリのソースコードを直接書くことは禁止。
（Lead が編集してよいもの: breezing-active.json, Plans.md のマーカー更新のみ）
Philosophy
「Claude は指揮とレビュー、Codex が手を動かす」
delegate mode で Lead は調整に専念。 実装は Codex MCP 経由で Codex Implementer が実行。 レビューは独立 Reviewer。三者分離の完全自律。
Quick Reference
/breezing-codex 全部やって # Plans.md 全タスクを完走（Codex 実装）
/breezing-codex 認証機能からユーザー管理まで # 範囲指定
/breezing-codex --parallel 2 ログイン機能 # 並列数指定
/breezing-codex 続きやって # 前回中断から再開
/breezing との違い
| 特徴 | /breezing |
/breezing-codex |
|---|---|---|
| 実装担当 | Claude (task-worker) | Codex (codex-implementer) |
| 実装の仕組み | Sonnet が直接コーディング | Codex MCP 経由で委託 |
| レビュー担当 | Claude (code-reviewer) | Claude (code-reviewer) |
| Lead の役割 | delegate mode（調整専念） | delegate mode（調整専念） |
| 品質保証 | セルフレビュー 4 観点 | AGENTS_SUMMARY + Quality Gates |
| ファイル分離 | owns: アノテーション | Lead 判断（worktree or owns:） |
| コスト特性 | Claude トークン消費 | Codex API + Claude レビュー |
Feature Details
| Feature | Reference |
|---|---|
| Execution Flow | See references/execution-flow.md |
| Team Composition | See references/team-composition.md |
| Codex Impl Flow | See references/codex-impl-flow.md |
| Review/Retake Loop | See breezing: review-retake-loop.md |
| Plans.md → TaskList | See breezing: plans-to-tasklist.md |
| Session Resilience | See breezing: session-resilience.md |
| Guardrails Inheritance | See breezing: guardrails-inheritance.md |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 125 lines · 94 tokens per session scan A 6a04e9b2907b
breezing-codex is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 8mo ago), licensed MIT. It adds 94 tokens to every session and 1,946 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…