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
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.
git clone --depth 1 https://github.com/Chachamaru127/claude-code-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/commands/chachamaru127/claude-code-harness/handoff-to-claude)<a href="https://agentmods.dev/commands/chachamaru127/claude-code-harness/handoff-to-claude"><img src="https://agentmods.dev/badge/commands/chachamaru127/claude-code-harness/handoff-to-claude/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/commands/chachamaru127/claude-code-harness/handoff-to-claude"><img src="https://agentmods.dev/badge/commands/chachamaru127/claude-code-harness/handoff-to-claude.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 | $0.00012 | $0.00463 |
| Opus 5 | $0.00006 | $0.00231 |
| Sonnet 5 | $0.00002 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
handoff-to-claude 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 10d 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.
What it actually says
/handoff-to-claude
あなたは Cursor (PM) です。Claude Code に渡す依頼文を、コピー&ペーストできる形で生成してください。
入力
- @Plans.md（対象タスクを特定）
- 可能なら
git status -sbとgit diff --name-only
出力（そのままClaude Codeに貼る）
次の Markdown を出力してください：
/claude-code-harness:core:work
<!-- ultrathink: PM からの依頼は原則重要タスクのため、常に high effort を指定 -->
ultrathink
## 依頼
以下を実装してください。
- 対象タスク:
- （Plans.md から該当タスクを列挙）
## 制約
- 既存のコードスタイルに従う
- 変更は必要最小限
- テスト/ビルド手順があれば提示
## 受入条件
- （3〜5個）
## Evals（採点/検証）
Plans.md の「評価（Evals）」に従って、**outcome/transcript を採点できる形**で進めてください。
- tasks（シナリオ）:
- （例: 具体的な入力/手順/期待結果）
- trials（回数/集計）:
- （例: 3回、成功率 + 中央値）
- graders（採点）:
- outcome:
- （例: unit tests / typecheck / ファイル状態）
- transcript:
- （例: 禁止行為なし / 余計な変更なし）
- 実行コマンド（可能なら）:
- （例: `npm test`, `./tests/validate-plugin.sh` など）
## 参考
- 関連ファイル（あれば）
**作業完了後**: `/handoff-to-cursor` を実行して完了報告すること
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.
- 10d ago First seen · 59 lines · 12 tokens per session scan A df3adc5ca8c4
handoff-to-claude is a command published in the GitHub repository Chachamaru127/claude-code-harness (3,103 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 463 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.