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
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Chachamaru127/claude-code-harness/plugin install 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/skills/chachamaru127/claude-code-harness/harness-review)<a href="https://agentmods.dev/skills/chachamaru127/claude-code-harness/harness-review"><img src="https://agentmods.dev/badge/skills/chachamaru127/claude-code-harness/harness-review/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/claude-code-harness/harness-review"><img src="https://agentmods.dev/badge/skills/chachamaru127/claude-code-harness/harness-review.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 | $0.00050 | $0.05003 |
| Opus 5 | $0.00025 | $0.02501 |
| Sonnet 5 | $0.00010 | $0.01001 |
| Haiku 4.5 | $0.00005 | $0.00500 |
Grade A, and why
harness-review 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 3d 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Review
Harness の統合レビュースキル。
この SKILL.md は薄い dispatcher であり、詳細な品質基準は references/ を読む。
if $ARGUMENTS == "": → 「今までの作業のレビュー」と解釈し、Review target detection を実行する → review target が 1 つに確定できる場合だけ自動開始する → review target が不明または複数候補の場合は AskUserQuestion で選択肢を出し、認識を揃えてから開始する
Output Contract (P35: 「止まったように見える」UX 対策)
<local-command-stdout> で host へ結果を中継する場合だけ、output の 最後の 1 行に次の literal を含める:
↑この結果は Claude が要約します。Enter キーで次へ進むか、新規 prompt で別の指示を出してください。
これは <local-command-stdout> 経由で text response として表示されると user が「止まった」と感じる UX 問題への明示的な instruction (patterns.md P35)。
host の最終回答は verdict、判断理由、確認した証拠、未検証点を返す。要約の予告だけで終了しない。
Dispatcher Contract
この skill の責務は review 判定だけ。 commit / push / release は既定では行わない。
- review default read-only boundary: 既定は read-only。
APPROVEでも自動 commit しない - Do not push just to review: review 目的だけで push しない
- commit が必要な場合は、ユーザー明示依頼、
harness-work、またはharness-releaseの Work Commit Gate に委譲する --commit-on-approveのような明示 opt-in が設計されるまで、この skill 単体の default side effect は禁止
Quick Reference
| Command | Mode | Purpose |
|---|---|---|
/harness-review |
code |
今までの作業を自動検出して review |
/harness-review --quick |
quick |
小さな dirty change を軽く closeout |
/harness-review --codex-closeout |
codex-closeout |
Codex 助言 + focused tests で closeout |
/harness-review --dual |
dual |
Claude + Codex second opinion |
--pre-review cursor |
code+pre-review |
fresh-context composer advisory pre-review before brain verdict（read-only） |
/harness-review --cursor |
code+cursor-second-opinion |
core review gates + cursor second-opinion（brain 一次レビュー必須） |
HARNESS_IMPL_BACKEND=cursor harness-review |
code+cursor-second-opinion |
default ON 時も core review gates に cursor second-opinion を自動加算。primary verdict は brain 固定 |
/harness-review --team-debate |
team-debate |
TeamAgent Debate を強制 |
/harness-review --security |
security |
security 専用 review |
/harness-review plan |
plan |
Plans.md の計画 review |
/harness-review scope |
scope |
scope creep / 漏れ review |
What ships with it
12 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.
- references/blind-judge.md 12 KB
- references/code-review.md 4.3 KB
- references/codex-closeout.md 2.8 KB
- references/cursor-review.md 6.1 KB
- references/dual-review.md 6.6 KB
- references/governance.md 3.4 KB
- references/plan-review.md 935 B
- references/scope-review.md 1.3 KB
- references/security-profile.md 16 KB
- references/team-debate.md 2.4 KB
- references/ui-rubric.md 3.7 KB
- references/vision-high-res-flow.md 8.4 KB
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.
- 3d ago Changed 5ed6b5c6ba59
- 9d ago First seen · 351 lines · 50 tokens per session scan A ad514cb4578b
harness-review is a skill published in the GitHub repository Chachamaru127/claude-code-harness (3,098 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 5,003 once invoked, about $0.0003 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…