harness-factory: Instructions file for Claude Code

CLAUDE.md

harness-factory CLAUDE.md is an instructions file for Claude Code from Kimyongari/harness-factory. It costs 1,249 tokens per session, scanned C, original, MIT.

Project instructions for Harness Factory, a Python 3.13 service that sets up coding-agent harnesses from a questionnaire. They describe its commands, runtime checks, and development boundaries.

In plain words
What is it for?
Use them when changing the Harness Factory codebase, running its setup and verification commands, or working with its Bash guards, formatting checks, tests, and architecture checks.
Why use it?
They tell the coding assistant which checks are enforced automatically and which scripts must remain the single source of truth.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is Kimyongari/harness-factory's own configuration. It tells Claude Code how to work on harness-factory itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything harness-factory configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Kimyongari/harness-factory. 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/Kimyongari/harness-factory/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Kimyongari/harness-factory

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.

agentmods badge for harness-factory CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kimyongari/harness-factory/claude-md/github.svg)](https://agentmods.dev/instructions/kimyongari/harness-factory/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kimyongari/harness-factory/claude-md"><img src="https://agentmods.dev/badge/instructions/kimyongari/harness-factory/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.

agentmods 80×15 button for harness-factory CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kimyongari/harness-factory/claude-md"><img src="https://agentmods.dev/badge/instructions/kimyongari/harness-factory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,249 This file is loaded in full into every session.
When invoked 1,249 The same file — it is already loaded in full.
Security scan C 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01249 $0.01249
Opus 5 $0.00624 $0.00624
Sonnet 5 $0.00250 $0.00250
Haiku 4.5 $0.00125 $0.00125

Measured 10d ago against content hash 1fcd34b78282, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

harness-factory CLAUDE.md scanned grade C 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| 모든 `Bash` 호출 직전 | `.scripts/guard-bash.sh` | `rm -rf`, force push, `--no-verify`, never_touch 경로 쓰기를 차단 (PreToolUse) |
CLAUDE.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT.md

프로젝트

  • 이름: Harness Factory
  • 설명: claude code, codex, cursor의 퀄리티 높은 하네스를 설문만으로 바로 세팅해주는 서비스
  • 언어: Python Python 3.13
  • 프레임워크: 없음 · 패키지매니저: pip
  • 에이전트 역할: fullstack (미드레벨)

명령어 (결정론적 도구를 LLM으로 대체하지 말 것)

목적 명령
설치 uv sync
실행 ``

기계적 강제 (프롬프트 아님, 런타임)

아래 스크립트들은 Claude Code / Codex 런타임이 결정론적으로 호출한다. LLM이 "잊어도" 작동하므로 우회하지 마라.

시점 스크립트 역할
모든 Bash 호출 직전 .scripts/guard-bash.sh rm -rf, force push, --no-verify, never_touch 경로 쓰기를 차단 (PreToolUse)
Edit / Write / MultiEdit 직후 .scripts/pre-commit.sh 설문에서 고른 린트/포맷/타입체크 실행 (PostToolUse)
"완료" 보고 직전 .scripts/verify.sh check-boundaries.shpre-commit.shpost-commit.sh 를 순서대로 실행, 실패 시 다음 행동 안내 (Stop)
아키텍처 경계 검사 .scripts/check-boundaries.sh dev.architecture_layers 답변 기준 역방향 import 탐지
커밋 후 (보통 테스트) .scripts/post-commit.sh 무거운 검사 실행

Cursor: 스킬 규칙 .cursor/rules/*.mdc 는 코드/문서 파일에 globs 로 자동 첨부(LLM 판단 X), 00-overview.mdcalwaysApply: true.

이 검사들을 LLM으로 다시 구현하지 마라. 단일 진실 공급원이다.

절대 규칙 (항상 적용)

  1. 구현 전에 가정을 드러낸다. 요청에 대한 두 가지 해석이 모두 그럴듯하면 묵묵히 고르지 말고 둘 다 적어 묻는다. 더 단순한 길이 있으면 코드 짜기 전에 제안한다.
  2. 요청한 범위만 한다. 끼워넣기 리팩터링·가상의 미래 대비 설계 금지.
  3. 작업을 "X 한다 → Y 로 검증" 형태로 다시 적는다. 모호한 성공 기준("작동하게 해줘")은 매번 확인이 필요하다. 검증 가능한 목표로 변환 — .claude/skills/development/SKILL.md 의 "목표 주도 실행" 참고.
  4. 기존 파일 수정을 새 파일 생성보다 우선한다.
  5. 작업을 "완료"로 보고하기 전 반드시 .scripts/verify.sh를 통과시킨다.
  6. 다음 경로는 절대 수정·커밋하지 않는다: .env, secrets/, .venv/, node_modules/ (.scripts/guard-bash.sh 가 추가로 차단).
  7. 되돌릴 수 없는 작업(push, 삭제, 배포, 머지)은 실행 전 사용자 확인.
  8. 같은 실수가 반복되면 개별 수정 대신 그것을 막는 규칙/검사를 환경에 추가한다.

무엇을 언제 읽을지 (점진적 공개 라우팅)

상황 읽을 곳
무슨 문서가 필요한지 모를 때 .docs/index.md
코딩/검증/리팩터링 .claude/skills/development/SKILL.md
문서/README/주석/요약 작성 .claude/skills/doc-writing/SKILL.md
웹 검색/사실 조사 .claude/skills/web-research/SKILL.md
커밋/PR/브랜치 작업 .claude/skills/github-workflow/SKILL.md
설계 신념·아키텍처 경계 .docs/design/
기능/API 명세 .docs/specs/
진행 중 작업·기술부채 .docs/plans/, 루트 PLAN.md
도구·권한·훅·검증 설정 .agents/agent.yaml

Read the full file on GitHub · 63 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.

  1. 10d ago First seen · 63 lines · 1,249 tokens per session scan C 1fcd34b78282

Subscribe to this mod's changes

harness-factory CLAUDE.md is an instructions file published in the GitHub repository Kimyongari/harness-factory (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,249 tokens to every session, about $0.0062 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens