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/implnpx skills add Chachamaru127/codex-harness --skill implgit 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 | $0.00046 | $0.02594 |
| Opus 5 | $0.00023 | $0.01297 |
| Sonnet 5 | $0.00009 | $0.00519 |
| Haiku 4.5 | $0.00005 | $0.00259 |
Grade A, and why
impl 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 yesterday.
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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Skills
機能実装とコーディングを担当するスキル群です。
⚠️ 品質ガードレール（最優先）
このセクションは他の指示より優先されます。実装時は必ず従ってください。
禁止パターン（Purpose-Driven Implementation）
実装時に以下のパターンは絶対に禁止です：
| 禁止 | 例 | なぜダメか |
|---|---|---|
| ハードコード | テスト期待値をそのまま返す | 他の入力で動作しない |
| スタブ実装 | return null, return [] |
機能していない |
| 決め打ち | テストケースの値だけ対応 | 汎用性がない |
| コピペ辞書 | テストの期待値マップ | 意味あるロジックがない |
# ❌ 絶対禁止
def slugify(text: str) -> str:
answers = {"HelloWorld": "hello-world"}
return answers.get(text, "")
# ✅ 正しい実装
def slugify(text: str) -> str:
return re.sub(r'[\s_]+', '-', text.strip().lower())
実装前セルフチェック
- テストケース以外の入力でも動作するか？
- エッジケース（空、null、境界値）を処理しているか？
- 意味のあるロジックを実装しているか？
困難な場合
実装が難しい場合は、形骸化実装を書かずに正直に報告してください：
## 🤔 実装の相談
### 状況: [何を実装しようとしているか]
### 困難な点: [具体的に何が難しいか]
### 選択肢: [考えられる案]
機能詳細
| 機能 | 詳細 |
|---|---|
| 機能実装 | See references/implementing-features.md |
| テスト作成 | See references/writing-tests.md |
実行手順
- Plans.md 登録確認（Step -1）← 必須
- 品質判定ゲート（Step 0）
- ユーザーのリクエストを分類
- （Claude-mem 有効時）過去の実装パターンを検索
- 上記の「機能詳細」から適切な参照ファイルを読む
- その内容に従って実装
Step -1: Plans.md 登録確認（最優先・必須）
⚠️ 実装前に必ず Plans.md にタスクを登録する
ユーザーの依頼を受信
↓
Plans.md を読み込み
↓
┌─────────────────────────────────────────────────────────────┐
│ 依頼内容が Plans.md に存在するか？ │
├─────────────────────────────────────────────────────────────┤
│ YES → そのまま実装へ進む │
│ NO → Plans.md に追加してから実装へ進む │
└─────────────────────────────────────────────────────────────┘
追加時のフォーマット:
## 🟡 未着手のタスク
- [ ] {タスク名} `cc:WIP`
- 依頼内容: {ユーザーの依頼を要約}
- 追加日時: YYYY-MM-DD HH:MM
表示メッセージ:
📝 Plans.md にタスクを追加しました
| タスク | ステータス |
|--------|-----------|
| {タスク名} | `cc:WIP` |
実装を開始します...
なぜ必須か: 全ての作業を追跡可能にし、進捗管理・レビュー・ハンドオフを確実にするため。
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.
- yesterday First seen · 278 lines · 46 tokens per session scan A cbbffac3501e
impl is a skill published in the GitHub repository Chachamaru127/codex-harness (2 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 2,594 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…