tsq-audit

tsq-audit is a skill for Claude Code from sonature-lab/timsquad. It costs 83 tokens per session (846 once invoked), scanned A, original, MIT.

A code-audit skill that reviews changed files and runs relevant verification checks. It produces a report grouped by severity across security, type safety, error handling, API compatibility, tests, and performance.

In plain words
What is it for?
Use it for pull-request reviews, pre-release checks, or phase gates to match changed files with checks such as tests and shell analysis, then report critical, high, medium, and low findings with fixes.
Why use it?
It catches common defects before a change is merged, including exposed secrets, unsafe type casts, missing error handling, breaking interface changes, missing tests, and performance problems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it for pull-request reviews, pre-release checks, or phase gates to match changed files with checks such as tests and shell analysis, then report critical, high, medium, and low findings with fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sonature-lab/timsquad/tsq-audit
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 sonature-lab/timsquad --skill tsq-audit
Clone the repo
git clone --depth 1 https://github.com/sonature-lab/timsquad

Made for: Claude Code.

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 tsq-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-audit/github.svg)](https://agentmods.dev/skills/sonature-lab/timsquad/tsq-audit)
Your own site
<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-audit"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-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.

agentmods 80×15 button for tsq-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/sonature-lab/timsquad/tsq-audit"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/tsq-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 846 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 $0.00083 $0.00846
Opus 5 $0.00042 $0.00423
Sonnet 5 $0.00017 $0.00169
Haiku 4.5 $0.00008 $0.00085

Measured 9d ago against content hash 5d998f7aefac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tsq-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 9d 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.

templates/base/skills/tsq-audit/SKILL.md · 75 lines

What it actually says

Code Audit

변경 파일 기반 감사를 수행하여 품질 게이트를 통과하도록 돕는다. 별도 컨텍스트(fork)에서 실행하여 구현자와 독립된 판단을 보장한다.

Contract

  • Trigger: /tsq-audit 호출 또는 Phase gate 전 품질 확인
  • Input: 현재 변경 파일 목록 + 관련 스킬 Verification
  • Output: 스킬별 Verification 결과 + 6관점 severity별 리포트
  • Error: Verification 실패 시 해당 항목 + 수정 가이드 출력
  • Dependencies: coding, testing, security

Protocol

  1. 변경 수집: git diff --name-only 또는 staged changes로 대상 수집
  2. 스킬 매칭: 변경 파일 확장자/경로 기반으로 관련 스킬 자동 감지
    • .ts/.tsx → coding, typescript 스킬
    • test 포함 경로 → testing 스킬
    • security, auth, middleware → security 스킬
    • .sh 파일 → security 스킬 (shellcheck)
    • schema, migration → database 스킬
  3. Verification 실행: 매칭된 각 스킬의 Verification 테이블에서 Command 실행
  4. 6관점 분석: 변경 코드를 아래 관점에서 분석
  5. 리포트 생성: severity별 구조화된 결과 출력

6관점 분석

관점 점검 항목
보안 OWASP Top 10, 시크릿 노출, injection, XSS
타입 안전성 any 타입, 타입 단언(as), 미검증 캐스팅
에러 핸들링 catch 누락, 에러 무시, 불완전한 에러 처리
API 호환성 기존 인터페이스 변경, breaking changes
테스트 커버리지 변경 코드의 테스트 존재 여부
성능 N+1 쿼리, 불필요한 리렌더링, 메모리 누수

Report Format

## Audit Report
### CRITICAL (즉시 수정)
- [CRITICAL] src/auth.ts:42 — SQL injection 가능성
### HIGH (머지 전 수정)
- [HIGH] src/api.ts:15 — 에러 핸들링 누락
### MEDIUM (개선 권장)
- [MEDIUM] src/utils.ts:8 — any 타입 사용
### LOW (참고)
- [LOW] src/config.ts:3 — 매직넘버 사용

Verification

Check Command Pass Criteria
변경 파일 감지 git diff --name-only 1개 이상 변경 파일
스킬 Verification 관련 스킬 체크 실행 모든 체크 통과
6관점 커버리지 6가지 관점 체크 모든 관점 포함
severity 분류 구조화 리포트 severity 태그 존재
파일/라인 참조 코드 위치 명시 정확한 위치 참조
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. 9d ago First seen · 75 lines · 83 tokens per session scan A 5d998f7aefac

Subscribe to this mod's changes

tsq-audit is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 9d ago), licensed MIT. It adds 83 tokens to every session and 846 once invoked, about $0.0004 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.

Related

Other skills, from other repositories