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.
npx skills add scroogy-dev/scroogy-agent-skills --skill git-review-quizgit clone --depth 1 https://github.com/scroogy-dev/scroogy-agent-skillsWrote 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/scroogy-dev/scroogy-agent-skills/git-review-quiz)<a href="https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/git-review-quiz"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/git-review-quiz/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/scroogy-dev/scroogy-agent-skills/git-review-quiz"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/git-review-quiz.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 | $0.00097 | $0.05470 |
| Opus 5 | $0.00048 | $0.02735 |
| Sonnet 5 | $0.00019 | $0.01094 |
| Haiku 4.5 | $0.00010 | $0.00547 |
Grade A, and why
git-review-quiz 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 5d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
개요
PR(pull request) 리뷰나 셀프 리뷰에 들어가기 전에 변경을 얼마나 이해했는지 문항으로 점검합니다. 대상의 diff에서 비즈니스·테크 문항을 만들어 대화형으로 풀거나 PR 댓글로 게시합니다.
- 경계: 이 스킬은 이해도를 묻습니다. 결함 지적과 위험도 산출은 git-review가 담당하며 여기서는 하지 않습니다.
- 두 가지 방식: 대화형 진행(기본)과
--comment게시. - 산출 파일: 대화형은
.ai/99_workspace/temp_review_quiz.md,--comment는.ai/99_workspace/temp_review_quiz_comment.md. - 형식 SSoT: 이 skill 디렉토리의
templates/quiz-template.md가 산출 파일 형식의 원본이고,scripts/check-quiz.sh가 그 형식을 판정합니다.
관련 skill
- git-review (독립): 서로 호출하지 않습니다. 테크 문항의 소재 축인 7 카테고리 체계의 원본이 git-review에 있으므로, 한쪽을 고치면 양쪽을 동기화합니다.
- git-review-context (참고):
.ai/99_workspace/temp_review_context.md가 있으면 변경 요약으로 참고합니다. 자동 호출하지 않습니다. - git-pr-feedback (참고): 대상 PR 식별과 댓글 게시 규칙의 원본입니다. 이 스킬은 핵심만 옮겨 담은 사본이므로, 한쪽을 고치면 양쪽을 동기화합니다.
- ai-workspace (권장):
.ai/99_workspace/경로에 산출 파일을 씁니다. 구조가 없으면 필요한 디렉토리를 직접 생성합니다.
참조 문서
- 공통 규칙:
.ai/10_rules/context-loading.md(있으면 따르며, 이미 적재되어 있으면 재로딩하지 않습니다) - 스킬 고유 추가 참조:
.ai/30_contract/index.md,.ai/40_domain/index.md(비즈니스 문항의 근거 문서 목차. index를 먼저 읽고 변경과 관련 있는 파일만 선택적으로 읽습니다).ai/60_codebase/index.md(변경 지점의 호출 흐름 파악. SSoT는 소스코드이므로 색인을 신뢰하지 않고 실제 코드를 확인합니다).ai/10_rules/writing-principles.md·.ai/10_rules/writing-principles-local.md(있으면 산출물 작성 원칙으로 참조. 충돌 시 local 우선이고, 없으면 본문의 "산출물 접기 기준"이 기본값입니다)
실행 절차
아래 순서로 진행합니다. 각 단계의 세부 규칙은 같은 이름의 섹션을 참조합니다.
1단계: 대상 식별
이 단계의 저장소 확정·
--repo·--hostname규칙은git-pr-feedback/SKILL.md"대상 PR 식별"에서 핵심만 옮긴 사본입니다. 한쪽을 고치면 양쪽을 동기화합니다.
- 최초 조회 전에 대상 저장소를 확정합니다. 현재 브랜치의 upstream 원격(없으면
origin)의 URL을 정규화해 호스트/소유자/저장소를 얻고, 원격이 없거나 후보가 복수면 사용자에게 질의합니다. - 인자로 PR 번호를 받으면 그 PR을 대상으로 합니다. 인자가 없으면 현재 브랜치의 열린 PR을 자동 감지하고, 감지에 실패하면 브랜치 모드로 진행합니다.
- 최초
gh pr view부터--repo '<호스트>/<소유자>/<저장소>'를 명시합니다. 무보호로 조회하면GH_REPO·GH_HOST환경 변수나 실행 디렉토리가 다른 저장소의 동명 PR을 선택하고, 그 응답을 불변값으로 보관하면 잘못된 대상이 그대로 고정됩니다. - 조회 응답의 PR URL이 확정한 저장소와 일치하는지 확인한 뒤, 호스트/소유자/저장소·PR 번호·URL·
headRefOid·baseRefName·baseRefOid를 불변값으로 보관합니다.headRefOid와baseRefOid는 permalink의 커밋 SHA 기준값입니다. - 이후
gh pr계열 명령에는--repo를,gh api계열 명령에는--hostname '<호스트>'를 명시합니다.gh api의 기본 호스트는 github.com이라, GitHub Enterprise를 다룰 때 호스트를 생략하면 같은 소유자/저장소·번호의 무관한 github.com PR을 읽게 됩니다.
What ships with it
47 files 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.
- scripts/check-quiz.sh 16 KB runs code
- templates/quiz-template.md 3.5 KB
- tests/fixtures/invalid-comment-permalink-anchor.md 2.2 KB
- tests/fixtures/invalid-comment-permalink-branch.md 2.2 KB
- tests/fixtures/invalid-comment-permalink-http.md 2.2 KB
- tests/fixtures/invalid-comment-permalink-missing.md 2.1 KB
- tests/fixtures/invalid-comment-record.md 2.3 KB
- tests/fixtures/invalid-r1-header-no-bracket.md 439 B
- tests/fixtures/invalid-r1-header-no-number.md 430 B
- tests/fixtures/invalid-r1-header-unrecognized.md 972 B
- tests/fixtures/invalid-r1-number-skip.md 766 B
- tests/fixtures/invalid-r1-perspective.md 486 B
- tests/fixtures/invalid-r2-location-format.md 475 B
- tests/fixtures/invalid-r2-location-not-first.md 482 B
- tests/fixtures/invalid-r2-missing-location.md 435 B
- tests/fixtures/invalid-r3-details-close-before-open.md 668 B
- tests/fixtures/invalid-r3-details-extra-close.md 444 B
- tests/fixtures/invalid-r3-details-unclosed.md 419 B
- tests/fixtures/invalid-r3-hint-duplicate.md 527 B
- tests/fixtures/invalid-r3-hint-none.md 382 B
- tests/fixtures/invalid-r4-answer-before-hint.md 474 B
- tests/fixtures/invalid-r4-answer-blank-explanation.md 500 B
- tests/fixtures/invalid-r4-answer-empty.md 417 B
- tests/fixtures/invalid-r4-answer-format.md 559 B
- tests/fixtures/invalid-r4-answer-no-basis.md 459 B
- tests/fixtures/invalid-r4-answer-no-policy-basis.md 584 B
- tests/fixtures/invalid-r4-answer-none.md 346 B
- tests/fixtures/invalid-r4-hint-answer-same-block.md 427 B
- tests/fixtures/invalid-r4-open-answer-comment-only.md 519 B
- tests/fixtures/invalid-r4-open-answer-no-model.md 470 B
- tests/fixtures/invalid-r5-answer-letter-unknown.md 506 B
- tests/fixtures/invalid-r5-label-duplicate.md 476 B
- tests/fixtures/invalid-r5-label-not-start-a.md 494 B
- tests/fixtures/invalid-r5-label-skip.md 486 B
- tests/fixtures/invalid-r5-mcq-option-after-details.md 538 B
- tests/fixtures/invalid-r5-open-options-after-answer.md 545 B
- tests/fixtures/invalid-r5-open-options-after-hint.md 545 B
- tests/fixtures/invalid-r5-open-with-options.md 469 B
- tests/fixtures/invalid-r5-too-few-options.md 453 B
- tests/fixtures/invalid-r6-answer-outside-details.md 493 B
- tests/fixtures/invalid-r7-duplicate-target.md 537 B
- tests/fixtures/invalid-r7-no-questions-heading.md 479 B
- tests/fixtures/invalid-r7-record-between-questions.md 856 B
- tests/fixtures/invalid-r7-zero-questions.md 291 B
- tests/fixtures/valid-comment.md 2.4 KB
- tests/fixtures/valid-interactive.md 2.9 KB
- tests/run-tests.sh 13 KB runs code
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.
- 5d ago First seen · 269 lines · 97 tokens per session scan A 3df30f8d428a
git-review-quiz is a skill published in the GitHub repository scroogy-dev/scroogy-agent-skills (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 97 tokens to every session and 5,470 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
ss-learn
Capture a human-approved UI design lesson as a privacy-minimized local StyleSeed candidate, review it, and prepare an opt-in share package without transmitting project code, prompts, screenshots, or brand data. Use when a person asks StyleSeed to remember, learn from, generalize, review, or prepare a reusable rule…
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
vertical-hr-recruiting
Domain-knowledge primer for the HR & recruiting vertical (ATS, onboarding, workforce scheduling, engagement). Applied by architect/pm during spec authoring so they aren't naive about hiring pipelines, the admitted offer→onboard data-carry gap, EEO/I-9 compliance, and shift-coverage rules. Stops the four products from…
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
vertical-retail
Retail & e-commerce domain knowledge for SMB storefront products (storefront, inventory, pricing, cart-recovery). Codifies the vocabulary (SKU vs variant, reorder point, COGS/margin, ATS, AOV), the non-obvious rules (Shopify owns the storefront — don't fight it head-on; the wedge is multichannel inventory + reorder…
vertical-fitness
Domain-knowledge pack for fitness & wellness (boutique studios, gyms, coaches, on-demand brands) — the membership vocabulary, non-obvious billing/booking rules, and retention realities a builder must know so fitness products aren't speced naive. Covers the four products this niche ships (class-booking, coaching…