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 issue-auditgit 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/issue-audit)<a href="https://agentmods.dev/skills/scroogy-dev/scroogy-agent-skills/issue-audit"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/issue-audit/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/issue-audit"><img src="https://agentmods.dev/badge/skills/scroogy-dev/scroogy-agent-skills/issue-audit.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 | $0.00092 | $0.11935 |
| Opus 5.5 | $0.00037 | $0.04774 |
| Sonnet 5.5 | $0.00018 | $0.02387 |
| Haiku 4.5 | $0.00009 | $0.01193 |
Grade A, and why
issue-audit 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 2d 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 — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.
개요
이슈 스펙(요구사항) 대비 구현을 독립 감사인 관점에서 검증합니다. 구현을 수행한 AI가 아닌 다른 모델이 실행하는 것을 전제로, 두 단계로 감사를 수행합니다.
- 1단계 — 적합성 검증: 스펙 대비 구현 완료 여부를 항목별로 대조
- 2단계 — 비판적 검증: 구현이 잘못되었을 수 있는 근거를 적극적으로 탐색
이 기본 모드를 최종 감사라 부릅니다. 구현이 끝난 뒤 이슈 전체(스펙·구현·문서)를 검증하기 때문입니다.
--plan 옵션은 구현 전 spec·plan을 감사하는 계획 감사 모드입니다 (## 옵션 참조).
관련 skill
- issue-work (권장):
.ai/90_issues/의 스펙·계획·요약 파일을 감사 입력으로 활용합니다.issue-work계획의 마지막 고정 **Task N(교차모델 검증)**에서 이 스킬을 호출합니다. 구현 모델과 다른 벤더 모델(Non-Anthropic 포함)로 사용자가 직접 수동 수행하며, 감사 결과는issue-<번호>-summary.md의 모델 기록·Task별 결과에 반영합니다. 계획 종료 게이트 뒤의 계획 감사(--plan)도 issue-work가 수행 여부를 질의하고 사용자가 직접 실행합니다. 결과는 같은 summary의계획 audit 모델행과계획 감사줄에 반영합니다. - ai-workspace (권장):
.ai/30_contract/,.ai/40_domain/문서를 비즈니스 검증에 참조합니다.
git-review와의 차이: git-review는 PR 단위 코드 품질 리뷰이고, issue-audit는 이슈 단위 스펙 충족 + 비판적 검증입니다.
참조 문서
- 공통 규칙:
.ai/10_rules/context-loading.md— 있으면 따르며, 이미 적재되어 있으면 재로딩하지 않습니다. - 스킬 고유 추가 참조:
.ai/90_issues/active/하위 전체 또는.ai/90_issues/archive/issue-<번호>/전체.ai/30_contract/index.md,.ai/40_domain/index.md— 도메인·계약 정합성 (index 먼저 → 관련 파일만 선택적으로).ai/50_adr/index.md— 1단계 경계 검증 시 ADR과의 정합성 대조 (index 먼저 → 관련 ADR만 선택적으로).ai/60_codebase/index.md— 관련 기능의 호출 흐름.ai/70_ledger/index.md— 이미 수용된 known issue·기술부채 대조 (index 먼저 → 관련 항목만 선택적으로).ai/10_rules/writing-principles.md·.ai/10_rules/writing-principles-local.md— 있으면 산출물 작성 원칙으로 참조 (충돌 시 local 우선; 없으면 본문의 "산출물 접기 기준"이 기본값).ai/10_rules/testing-principles.md·.ai/10_rules/testing-principles-local.md— 있으면 테스트 실행 원칙으로 참조해[D]검증 명령의 실행 셸·전제 조건을 정한다 (우선순위는 local >testing-principles.md> 이 skill의 절차; 없으면 현재 절차 그대로)
역할 원칙
이 스킬을 실행하는 AI는 독립 감사인입니다.
- 구현자의 의도를 선의로 해석하지 않는다.
- "동작하니까 괜찮다"가 아니라 "스펙에 명시된 대로인가"를 기준으로 판단한다.
- 스펙 자체의 모호함이나 누락도 발견 사항으로 보고한다.
입력
사용자로부터 아래 정보를 확인합니다.
| 항목 | 필수 | 설명 |
|---|---|---|
| 이슈 번호 | O | GitHub Issue 번호 또는 이슈 식별자 |
| 구현 브랜치 | △ | 미지정 시 현재 브랜치 사용 |
What ships with it
5 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.
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.
- 2d ago Changed · +25 lines · +8 tokens per session 237df2ed6814
- 7d ago Changed · +2 lines c87b85618980
- 9d ago Changed · +14 lines 0443e08b9476
- 11d ago Changed dbf2e81cd406
- 20d ago Changed 6a034b87a23d
- 25d ago Changed 29ca9bf79de8
- 1mo ago Changed · +4 lines 3af8e86734a8
- 1mo ago Changed · +46 lines · +39 tokens per session a8d92cf301fd
- 1mo ago Changed · +103 lines cdfdd3e26140
- 2mo ago First seen · 295 lines · 45 tokens per session scan A 3048d211764e
issue-audit is a skill published in the GitHub repository scroogy-dev/scroogy-agent-skills (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 92 tokens to every session and 11,935 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…