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/commands/eval.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/commands/claude-code-expert/carve-harness/eval)<a href="https://agentmods.dev/commands/claude-code-expert/carve-harness/eval"><img src="https://agentmods.dev/badge/commands/claude-code-expert/carve-harness/eval/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/commands/claude-code-expert/carve-harness/eval"><img src="https://agentmods.dev/badge/commands/claude-code-expert/carve-harness/eval.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 | $0.00032 | $0.00531 |
| Opus 5.5 | $0.00013 | $0.00212 |
| Sonnet 5.5 | $0.00006 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
eval 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
carve-eval 워크플로를 실행하라. $ARGUMENTS가 있으면 인자로 해석한다({ goldenset?: glob, threshold?: 70, delta?: 3, target?: "session"|"claude"|"exec:<cmd>" }).
- Phase 0 프리플라이트:
carve-validate.sh가 골든셋 구조를 먼저 검증한다(에이전트 0회). 실패하면 런을 시작하지 않는다 — 설정 오류가 "에이전트가 못했다"로 위장해 0점이 되는 것을 막는다. specs/goldenset/*.json의 고정 케이스(입력→루브릭)를 케이스별 k회 실행해 채점한다.- 채점: 결정론 assert(contains·regex·부정형)는 워크플로가 순수 채점,
llm-rubric은 evaluator가 판정. green = 전부 통과. pass@k(능력)·pass^k(일관성)를 분리 산출하고,suiteScore를specs/eval-score.json에 append(추이).- 직전 baseline 대비
delta(기본 3pt) 초과 하락 시[REGRESSION]으로 보고한다. - 케이스
version이 직전 run과 다르면[VERSION CHANGED]로 알린다 — 같은 문제를 푼 점수가 아니므로 baseline 비교를 그대로 신뢰하면 안 된다. - 채점·근거는
eval-run.sh가 만든다:specs/eval-runs/run-<N>/<id>#<i>.json에 응답 원문과 assert별 판정. 추이 append는eval-trend.sh(변조 시 거부). - 골든셋이 없으면 먼저
eval-goldenset스킬로 케이스를 작성하라(실제 실패 20~50건으로 시작). - 케이스를 새로 쓰거나 고쳤으면
bash .claude/hooks/carve-validate.sh --red로 "그 케이스가 실제로 무언가를 재는지"까지 확인하라.
$ARGUMENTS
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 · +4 lines 814b3139f27d
- 1mo ago First seen · 13 lines · 32 tokens per session scan A 4b8e21a1e683
eval is a command published in the GitHub repository claude-code-expert/carve-harness (15 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 531 once invoked, about $0.0001 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 commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
verify
Run repository verification using the verification-loop skill.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
constraints
A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.
check-dev
Type-check a Z specification with fuzz.