meta-skill-tester

meta-skill-tester is a skill for Claude Code from modu-ai/moai-cowork. It costs 154 tokens per session (4,124 once invoked), scanned A, original, Apache-2.0.

A testing tool for checking the quality of coding-agent skills. It compares results with and without a skill, runs regression and chain tests, measures usage and time, and produces a scored report.

In plain words
What is it for?
Use it to run A/B tests, regression tests, chain tests, rubric scoring, and comparisons of output quality, accuracy, completeness, token use, and time.
Why use it?
It reveals whether a skill actually improves results and whether later edits cause regressions. A baseline is the comparison result produced without the skill.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the moai-coworker plugin — 32 skills shipped together

Good fit Use it to run A/B tests, regression tests, chain tests, rubric scoring, and comparisons of output quality, accuracy, completeness, token use, and time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/meta-skill-tester
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add modu-ai/moai-cowork --skill meta-skill-tester
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-coworker, the plugin that ships this one along with the rest of its 32 skills.

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 meta-skill-tester

README.md
[![agentmods](https://agentmods.dev/badge/skills/modu-ai/moai-cowork/meta-skill-tester/github.svg)](https://agentmods.dev/skills/modu-ai/moai-cowork/meta-skill-tester)
Your own site
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/meta-skill-tester"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/meta-skill-tester/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 meta-skill-tester

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/meta-skill-tester"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/meta-skill-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00154 $0.04124
Opus 5.5 $0.00062 $0.01650
Sonnet 5.5 $0.00031 $0.00825
Haiku 4.5 $0.00015 $0.00412

Measured 27d ago against content hash e10d820a396e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meta-skill-tester 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 27d 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.

plugins/moai-coworker/skills/meta-skill-tester/SKILL.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Tester — 스킬 품질 검증 도구 (루브릭 + 체인 내장)

moai-coworker | revfactory/harness 테스트 방법론 기반 single source of truth for: 4차원 스코어링 루브릭, 스킬 체인 검증 프로토콜

개요

meta-skill-builder로 생성된 스킬 또는 기존 스킬을 검토합니다. 대상 호스트에서 실행할 수 있으면 스킬 사용 전후 결과를 비교하고, 실행하지 못한 검사는 별도로 표시합니다. 4차원 평가 기준과 체인 검증 절차를 이 문서에 담았습니다.

트리거 키워드

스킬 테스트 검증 A/B 테스트 baseline 회귀 테스트 체인 테스트 meta-skill-tester 품질 측정 루브릭 스코어링 4차원 평가

워크플로우

1. [로드]    → 대상 스킬의 tests/test-cases.yaml 로드
2. [선택]    → 테스트 모드 선택 (A/B | 회귀 | 체인 | 루브릭 단독)
3. [실행]    → 사용 가능한 대상 호스트에서 테스트 프롬프트 실행
4. [기록]    → 실행 환경, 입력, 실제 출력과 확인 가능한 측정값 기록
5. [스코어]  → 관측한 결과에만 4차원 루브릭 적용
6. [비교]    → 비교 실행이 있을 때만 baseline과 with-skill 비교
7. [보고]    → PASS / FAIL / NOT-RUN과 미확인 항목 기록

실행 규칙

테스트 모드

Mode 1: A/B 테스트 (신규 스킬 검증)

meta-skill-builder Phase 5에서 사용하는 기본 모드입니다.

절차:

  1. Baseline 실행: 대상 호스트에서 스킬 없이 동일 프롬프트 실행
  2. With-Skill 실행: 같은 호스트·모델·설정에서 스킬을 로드한 뒤 실행
  3. 두 실행의 입력, 출력, 도구 호출, 모델과 설정을 기록합니다. 실행할 수 없으면 NOT-RUN으로 보고합니다.
  4. 비교 측정:
메트릭 측정 방법 판정
토큰 사용량 호스트가 사용량을 제공할 때만 input + output 토큰 관측값과 차이 보고
출력 품질 관측한 결과를 동일 루브릭으로 평가 점수와 근거 보고
정확성 실행한 assertion의 통과율 사전 정의한 기준과 비교
완전성 필수 출력 포함 여부 누락 항목 보고

반복 실행 횟수는 결과 변동성과 판단 목적에 맞춰 정합니다. 한 번의 예시는 전체 호스트의 성능을 대표하지 않습니다.

Mode 2: 회귀 테스트 (기존 스킬 수정 후)

스킬 수정 시 기존 테스트 케이스가 여전히 통과하는지 확인합니다.

절차:

  1. 수정 전 실제 테스트 결과가 있으면 동일 호스트·설정의 baseline으로 로드
  2. 수정 후 동일 테스트 케이스 재실행
  3. 비교: 기존 통과 항목이 미통과로 변경되면 regression

회귀 판정:

변화 판정
기존 통과 → 여전히 통과 PASS
기존 통과 → 미통과 REGRESSION (수정 롤백 필요)
기존 미통과 → 통과 IMPROVEMENT
새로운 테스트 추가 INFO (비교 불가)
이전 실행 결과 없음 NOT-RUN (회귀 비교 불가)
Mode 3: 체인 테스트 (스킬 조합 검증)

여러 스킬이 순차적으로 연결되는 체인을 테스트합니다. 실제로 존재하고 실행 가능한 체인만 실행 대상으로 삼고, 나머지는 미실행으로 기록합니다.

3-1. Chain Definition Format
chain:
  name: "blog-publishing"
  description: "Blog post creation → AI slop review → optional media generation"
  steps:
    - skill: "moai-marketer:content-blog"
      output_type: "markdown"
      provides: ["blog_draft"]
    - skill: "moai-coworker:ai-slop-reviewer"
      input_from: ["blog_draft"]
      output_type: "markdown"
      provides: ["reviewed_draft"]
    - skill: "moai-media:media-higgsfield-image"
      input_from: ["reviewed_draft"]
      output_type: "image_url"
      optional: true
      provides: ["cover_image"]

Read the full file on GitHub · 383 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. 27d ago Changed · +1 lines e10d820a396e
  2. 1mo ago Changed · -4 lines · -37 tokens per session 64db0d9ede5a
  3. 2mo ago First seen · 386 lines · 191 tokens per session scan A 3dd98e7a518f

Subscribe to this mod's changes

meta-skill-tester is a skill published in the GitHub repository modu-ai/moai-cowork (316 stars, last pushed 25d ago), licensed Apache-2.0. It adds 154 tokens to every session and 4,124 once invoked, about $0.0006 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 2026-09-03.