Borrowing it
Nothing to install: this file belongs to claude-code-expert/carve-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.
curl -O https://raw.githubusercontent.com/claude-code-expert/carve-harness/main/CLAUDE.mdgit clone --depth 1 https://github.com/claude-code-expert/carve-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/instructions/claude-code-expert/carve-harness/claude-md)<a href="https://agentmods.dev/instructions/claude-code-expert/carve-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/claude-code-expert/carve-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.
<a href="https://agentmods.dev/instructions/claude-code-expert/carve-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/claude-code-expert/carve-harness/claude-md.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 | $0.00700 | $0.00700 |
| Opus 5.5 | $0.00280 | $0.00280 |
| Sonnet 5.5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
carve-harness CLAUDE.md 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 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.
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
CLAUDE.md — 프로젝트 가드레일 (하네스 전역 규칙)
하네스의 "제약" 기둥. 언어 무관 항상 적용. 스택별 규칙은
.claude/rules/에서 glob 자동 로드.
하네스 3기둥
- 제약: 이 파일 +
.claude/rules/*+ PreToolUse 차단 훅 - 피드백: PostToolUse(포맷·린트) + Stop(빌드·타입·테스트) + Evaluator 에이전트
- 상태: SessionStart/PreCompact 핸드오프 +
specs/(SDD 산출물)
절대 금지 (언어 무관)
- 자동 커밋 금지, 테스트 없는 개발 금지,
- 시크릿 하드코딩 금지 → 환경변수/시크릿 매니저
- 위험 git 금지: force push, 히스토리 재작성
- 기존 마이그레이션 수정 금지 → 새 버전만
- 미검증 완료 선언 금지 → 완료는
specs/의 완료 기준(SC)으로만
작업 원칙
- 한 번에 하나. 분해 후 진행. 모든 완료엔 검증 가능한 SC.
- 프로젝트 도메인 규칙: 이 자리에 프로젝트별 불변식·금지사항을 추가한다. (예: "주문 금액 음수 불가", "결제 승인 없이 배송상태 변경 금지")
응답 언어 프로토콜 (필수)
- 사용자 응답은 한국어로만 쓴다. 영어 요약을 앞에 두지 않는다.
- 코드·명령·파일명·에러 원문·기술 용어는 원문(English) 그대로 둔다.
- 에러 출력이나 영어 인용문이 있으면 그 부분에만 한 줄 한국어 설명을 붙인다.
- 응답은 핵심 요약으로 시작한다: 결과·판정을 첫 줄에, 근거는 그 아래에. 과정 서술 금지.
- 작업 완료 시 마지막 블록에 한 번만, 아래 3항목을 요약한다:
- 변경: 무엇을 변경했는지
- 이유: 왜 그렇게 했는지
- 주의: 주의할 점
스택 감지 (설치된 언어팩만 존재)
**/*.java→.claude/rules/java-spring/**/*.ts,**/*.tsx→.claude/rules/react-next/**/*.py→.claude/rules/python/·**/*.go→.claude/rules/go/·**/*.rs→.claude/rules/rust/- 검증 게이트·포맷·채점은
.claude/stacks/<pack>.sh가 정의 — 팩 추가/제거는bash install.sh pack add|remove
참고
- @AGENTS.md · @.claude/rules/common/
AI Context
Bash-hook + markdown harness repo — no application code. See .codesight/skills.md for the project slash-command list.
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 · +153 tokens per session 3c70ab18f96c
- 1mo ago First seen · 44 lines · 547 tokens per session scan A 8a0c277e528c
carve-harness CLAUDE.md is an instructions file published in the GitHub repository claude-code-expert/carve-harness (15 stars, last pushed 1mo ago), licensed MIT. It adds 700 tokens to every session, about $0.0028 per session on Opus 5.5. 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 instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.