Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/chachamaru127/codex-harness/codex-workernpx skills add Chachamaru127/codex-harness --skill codex-workergit clone --depth 1 https://github.com/Chachamaru127/codex-harnessWhat 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 | $0.00104 | $0.02681 |
| Opus 5 | $0.00052 | $0.01340 |
| Sonnet 5 | $0.00021 | $0.00536 |
| Haiku 4.5 | $0.00010 | $0.00268 |
Grade A, and why
codex-worker 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 2d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Worker Skill
Claude Code を PM/Orchestrator として、Codex を Worker として実装を委譲するスキル。
Philosophy
「Claude Code = 設計・レビュー、Codex = 実装」
高レベルな判断は Claude Code、実装の細部は Codex に任せる分業体制。
Quick Reference
- "Codex に実装させて" → this skill
- "Codex Worker" → this skill
- "Codex に作らせて" → this skill
- "実装を依頼" → this skill
Do NOT Load For (誤発動防止)
以下のキーワードは codex-review スキルが担当します（description と完全一致）:
| トリガーワード | 正しいスキル | 理由 |
|---|---|---|
| "Codex レビュー" | codex-review |
レビュー = 品質チェック |
| "セカンドオピニオン" | codex-review |
意見取得 ≠ 実装 |
| "Codex の意見" | codex-review |
意見 ≠ Worker |
| "Codex でレビュー" | codex-review |
レビュー目的 |
| "Codex セットアップ" | codex-review |
MCP 設定 |
Feature Details
| Feature | Reference |
|---|---|
| Setup | See references/setup.md |
| Worker Execution | See references/worker-execution.md |
| Task Ownership | See references/task-ownership.md |
| Parallel Strategy | See references/parallel-strategy.md |
| Quality Gates | See references/quality-gates.md |
| Review & Integration | See references/review-integration.md |
Execution Flow
1. タスク受信
↓
2. base-instructions 生成
- Rules 連結
- AGENTS.md 強制読み込み指示
↓
3. git worktree 準備（並列時）
↓
4. mcp__codex__codex 呼び出し
- prompt: タスク内容 + AGENTS_SUMMARY 証跡出力指示
- cwd: worktree パス
- approval-policy: never
- sandbox: workspace-write
↓
5. 結果検証
- AGENTS_SUMMARY 証跡確認
- 不合格時: 合計3回試行
↓
6. Orchestrator レビュー
- 品質ゲート（lint, test, 改ざん検出）
- 修正指示 → 再実行ループ
↓
7. マージ・Plans.md 更新
MCP Parameters (D20)
{
"prompt": "タスク内容 + AGENTS_SUMMARY 証跡出力指示",
"base-instructions": "Rules 連結 + AGENTS.md 強制読み込み指示",
"cwd": "/path/to/worktree",
"approval-policy": "never",
"sandbox": "workspace-write"
}
What ships with it
7 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.
- 2d ago First seen · 232 lines · 104 tokens per session scan A 7e401ec47732
codex-worker is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 104 tokens to every session and 2,681 once invoked, about $0.0005 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.