What is claude-code-harness CLAUDE.md?

Repository instructions for developing a Claude Code harness, which is a setup for running coding agents through plan, work, and review stages. It also describes this project's coding and release rules.

Use it when modifying the harness, following its development conventions, using its supported Claude Code features, or preparing a release.

It gives the agent the project context and prevents inconsistent changes, version updates, and commit messages.

How Chachamaru127/claude-code-harness configures Claude Code

About the project

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.

Chachamaru127/claude-code-harness · 3,189 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to Chachamaru127/claude-code-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Chachamaru127/claude-code-harness/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Chachamaru127/claude-code-harness

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/chachamaru127/claude-code-harness/claude-md/github.svg)](https://agentmods.dev/instructions/chachamaru127/claude-code-harness/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/chachamaru127/claude-code-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/chachamaru127/claude-code-harness/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/chachamaru127/claude-code-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/chachamaru127/claude-code-harness/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,136 This file is loaded in full into every session.

When invoked 4,136 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.04136	$0.04136
Opus 5.5	$0.01654	$0.01654
Sonnet 5.5	$0.00827	$0.00827
Haiku 4.5	$0.00414	$0.00414

Measured 1mo ago against content hash ca79110ccbac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

claude-code-harness CLAUDE.md scanned grade B with 1 finding 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 1mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

(user scope `~/.claude/settings.json` 等) の permissions 層が担い、ガードレール層は

CLAUDE.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Claude Harness Development Guide

This file provides guidance for Claude Code when working in this repository.

Project Overview

Claude harness is a plugin for autonomous operation of Claude Code in a "Plan → Work → Review" workflow.

Special note: This project is self-referential — it uses the harness itself to improve the harness.

Claude Code Feature Utilization

CC v2.1.111+ の統合機能を活用。詳細: docs/CLAUDE-feature-table.md Fable 5.1 / astra の担当別モデルと明示指定: docs/model-routing-policy.md 担当への目的、完成条件、証拠の受渡し: docs/prompt-calibration.md 長時間タスクの手順: docs/long-running-harness.md

主要活用機能: Agent Memory, Worktree isolation, Agent hooks, PreCompact/PostCompact, PermissionDenied tracking, 1M Context Window

Development Rules

Commit Messages

Follow Conventional Commits: feat: / fix: / docs: / refactor: / test: / chore:

Version Management

Keep all version surfaces in sync via ./scripts/sync-version.sh (the script is the SSOT for the target list — currently 7 strings across 6 files including .grok-plugin/plugin.json). Normal feature/docs PRs must leave both files unchanged and record changes under CHANGELOG.md's [Unreleased] section. Use ./scripts/sync-version.sh bump only when cutting a release.

CHANGELOG

Details: skills/harness-release/references/github-release.md (Keep a Changelog format; include Before/After tables for major changes)

Language

User-facing responses follow the explicit session or project language. If no language is configured, use English. Use Japanese only when i18n.language: ja, CLAUDE_CODE_HARNESS_LANG=ja, or an explicit session instruction requests Japanese output.

Full details (how to switch, precedence, what does not change): docs/i18n.md.

Read the full file on GitHub · 190 lines

Changes

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.

1mo ago Changed · +2 lines · +56 tokens per session ca79110ccbac
1mo ago Changed e735965825c6
1mo ago First seen · 188 lines · 4,080 tokens per session scan B eb93116299b8

Subscribe to this mod's changes

claude-code-harness CLAUDE.md is an instructions file published in the GitHub repository Chachamaru127/claude-code-harness (3,189 stars, last pushed 2d ago), licensed MIT. It adds 4,136 tokens to every session, about $0.0165 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

claude-code-harness: Instructions file for Claude Code