Claude Code Harness is a development workflow for coding agents that organizes work into planning, implementation, review, synchronization, and release stages. It helps developers keep specifications, tests, independent reviews, and release evidence connected while using tools such as Claude Code, Codex CLI, Cursor, or Grok.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Chachamaru127/claude-code-harnessnpx agentmods add skills/chachamaru127/claude-code-harness/harness-planWrote 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/claude-code-harness/harness-plan)<a href="https://agentmods.dev/skills/chachamaru127/claude-code-harness/harness-plan"><img src="https://agentmods.dev/badge/skills/chachamaru127/claude-code-harness/harness-plan.svg" alt="Measured on agentmods" 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 | $0.00052 | $0.06771 |
| Opus 5 | $0.00026 | $0.03386 |
| Sonnet 5 | $0.00010 | $0.01354 |
| Haiku 4.5 | $0.00005 | $0.00677 |
Grade C, and why
harness-plan scanned grade C with 2 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- 破壊的操作（`rm -rf`, migration destructive step, force push, production apply） Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 外部送信（`git push`, `gh pr create`, `gh api`, `curl` / API call, release / publish / deploy） How it starts
The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Plan
Harness の統合プランニングスキル。 以下の3つの旧スキルを統合:
planning(plan-with-agent) — アイデア → Plans.md への落とし込みplans-management— タスク状態管理・マーカー更新sync-status— Plans.md と実装の同期確認
Quick Reference
| ユーザー入力 | サブコマンド | 動作 |
|---|---|---|
"計画を作って" / /harness-plan create |
create |
Spec delta / skip reason → Plans.md task 生成 |
"タスクを追加して" / /harness-plan add |
add |
Plans.md に新タスク追加 |
"完了にして" / /harness-plan update |
update |
タスクマーカーを cc:完了 に変更 |
"今どこ？" / /harness-plan sync |
sync |
実装とPlans.mdを照合・同期 |
/harness-sync |
sync |
進捗確認（独立 sync surface と同等） |
/harness-plan create |
create |
spec.md / Plans.md 二正本の計画作成 |
/harness-plan list |
list |
plans/manifest.json の named Plans を一覧 |
/harness-plan switch <name> |
switch |
active plan を .claude/state/active-plan.json に保存 |
スコープ既定: 今進められる全作業（operator 裁定 2026-07-24）
計画依頼（create / 引数なし起動 / 「計画して」）の既定解釈は 「現時点で着手可能なすべての作業」。
- ユーザーが範囲を明示しない限り、依頼文脈に入る open item（残 phase、未処理 follow-up、既知の改善点、依頼文で言及された問題すべて）を洗い出して計画に含める。勝手に最小サブセットへ絞らない
- 件数が多い場合も絞り込みではなく、全量を Required / Recommended / Optional / Reject に分類して提示する。除外は Reject として理由を明示する（黙って落とさない）
- 「一部だけ先に」が妥当と判断する場合は、絞った計画ではなく、全量計画の中の実行順序（Phase 分割 / Depends）として表現する
この既定は計画候補の洗い出し範囲であり、実装や保護操作の承認ではない。評価・比較だけの依頼は評価を返し、採用済みの変更と提案を区別する。 task には目的と理由、担当範囲、検証可能な DoD、利用する証拠、原依頼や適用される承認の参照を残す。実装手順は契約上必要な制約以外を固定しない。
Literal companion commands（CC 2.1.108+）
/recap: 久しぶりに戻った時に要約を取り直してからsyncへ入る/undo:/rewindの別名。直前の plan 更新を即座に戻したい時にそのまま使う
サブコマンド詳細
標準の計画品質契約
See references/planning-quality.md
harness-plan は、spec.md product contract and Plans.md task contract の co-required planning output を作る planning surface である。
precedence は spec.md > sub-spec > Plans.md のまま維持する。
Plans.md は task ledger、root spec.md は product contract であり、上下関係は崩さない。
渡された情報をそのまま Plans.md に落とさない。
計画作成や大きな task 追加では、最新情報・既存仕様・記憶・TeamAgent / サブエージェントによる複数視点の議論を確認し、
このプロダクトに取り入れるべき要素だけを task contract に変換する。
/harness-plan create は Spec delta または Spec skip reason と Plans.md task 生成をセットで返す。
出力には必ず Spec delta または Spec skip reason を含める。
Spec delta / Spec skip reason は Harness が生成し、consumer は承認・修正だけ行う。
What ships with it
4 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.
- today Changed · +6 lines 3a3c2f4880f3
- 7d ago First seen · 402 lines · 52 tokens per session scan C 4a316b548866
harness-plan is a skill published in the GitHub repository Chachamaru127/claude-code-harness (3,091 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 6,771 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.