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/skills/carve-harness-create/SKILL.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/skills/claude-code-expert/carve-harness/carve-harness-create)<a href="https://agentmods.dev/skills/claude-code-expert/carve-harness/carve-harness-create"><img src="https://agentmods.dev/badge/skills/claude-code-expert/carve-harness/carve-harness-create/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/claude-code-expert/carve-harness/carve-harness-create"><img src="https://agentmods.dev/badge/skills/claude-code-expert/carve-harness/carve-harness-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 86 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00128 | $0.04345 |
| Opus 5 | $0.00064 | $0.02173 |
| Sonnet 5 | $0.00026 | $0.00869 |
| Haiku 4.5 | $0.00013 | $0.00434 |
Grade A, and why
carve-harness-create 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carve Harness — 프로젝트 맞춤 구성 (검증 · 보강 · 절단)
전체 설치된 하네스를 이 프로젝트에 맞춘다. 세 방향으로 동작한다:
- 검증(FIX) — CLAUDE.md·AGENTS.md·
.claude/CLAUDE.md설정 오류를 검출해 제안한다(자동 수정 아님). - 보강(ADD) — 감지된 스택에 필요한데 없는 요소(하네스 규칙·외부 개발도구·설정 스캐폴딩)를 채우도록 제안한다.
- 절단(PRUNE) — 이 스택에 불필요한 하네스 파일을 제거한다(되돌릴 수 있음).
프롬프트 주도이며 결정론 스크립트가 아니다. 분석 → 검증 → 보강 → 절단 → 통합제안 → 1회 확인 → 적용 → 평가표 순서를 반드시 지킨다. 파괴 인접 작업이다.
--dry-run인자가 오면 통합 제안표(5단계)까지만 하고 아무것도 바꾸지 않는다. 절단은bash install.sh rollback으로 되돌릴 수 있으나, 확인 없이 진행 금지. 설정 파일(CLAUDE.md 등) 편집은 사용자가 승인한 FIX 항목만 반영한다.
0. 전제 조건 점검
.claude/harness-manifest.txt가 있는가? 없으면 중단 — "설치된 하네스가 아닙니다. 먼저bash install.sh실행"이라고 보고하고 끝낸다.- git 작업트리가 clean인지 확인(
git status --porcelain). dirty면 경고만 하고 진행 가능 ("결과를 git diff로 검토·롤백하려면 clean 권장").
1. 프로젝트 전수 분석
스택·역할·규모 및 코드베이스 신호를 파악한다. 보수적 원칙: 확신 없으면 KEEP. 스택을 놓쳐 필요한 규칙을 삭제하는 false-negative가 가장 위험하다.
1-1. 언어/스택 (규칙 선택 근거)
- Java/Spring:
gradlew·build.gradle·build.gradle.kts·pom.xml, 또는find . -name '*.java' -not -path '*/.git/*' -not -path '*/build/*' | head -1 - TS/React/Next:
package.json+find . -name '*.tsx' -o -name '*.ts' | head -1. Next =package.json의"next"또는next.config.* - Python/FastAPI:
find . -name '*.py' -not -path '*/.venv/*' | head -1. FastAPI =grep -rl 'from fastapi' --include='*.py' . | head -1 - ORM/DB:
grep -rlE 'sqlalchemy|from django.db|@Entity|typeorm|prisma|drizzle' . | head -1 - 미지원(go/rs/rb 등): 감지돼도 대응 규칙 없음 → PRUNE 대상 아님(코어 훅이 커버).
1-2. 코드베이스 신호 (보강·평가 근거 — 새로 수집)
- 린터/포맷터 존재: Node면
package.json에prettier/eslint/biomedevDep + 로컬 바이너리; Python이면ruff/black(pyproject.toml또는 PATH); Java면 spotless 플러그인. - 테스트 유무:
tests/·test/·*_test.*·*.test.*·src/test/존재 여부(Stop 게이트 실효성 판단). - CI:
.github/workflows/·.gitlab-ci.yml존재. - 외부 도구 PATH:
command -v gh ruff prettier tsc npx— 스택에 필요한데 없는 것을 ADD 후보로. - 규모:
git ls-files | wc -l, 소스 디렉토리 수, 모노레포 신호(pnpm-workspace.yaml·turbo.json·workspaces·하위package.json2개+). 대규모 → fable 유지, 소형 단일 → 프루닝 후보.
What ships with it
1 file 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.
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 · +5 lines dadc7e1233bc
- 10d ago First seen · 185 lines · 128 tokens per session scan A 3d6d276caead
carve-harness-create is a skill published in the GitHub repository claude-code-expert/carve-harness (13 stars, last pushed yesterday), licensed MIT. It adds 128 tokens to every session and 4,345 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…