inspect

inspect is a skill for Claude Code from sonature-lab/timsquad. It costs 205 tokens per session (1,265 once invoked), scanned A, original, MIT.

A health-check skill for the TimSquad development framework. It compares code, documentation, hooks, skills, command-line tools, tests, and settings, then produces a Red/Amber/Green report.

In plain words
What is it for?
Use it to run build and test gates, check hooks and skills, compare CLI registrations with command files, detect documentation drift, review coverage gaps, and save a dated inspection report.
Why use it?
It finds mismatches that build up over time, such as documentation that no longer matches the code, missing registrations, dead code, or weak test coverage. This gives developers a checklist before a release or after a large change.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

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.

agentmods
npx agentmods add skills/sonature-lab/timsquad/inspect
Any agent
npx skills add sonature-lab/timsquad --skill inspect
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 inspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonature-lab/timsquad/inspect.svg)](https://agentmods.dev/skills/sonature-lab/timsquad/inspect)
Your own site
<a href="https://agentmods.dev/skills/sonature-lab/timsquad/inspect"><img src="https://agentmods.dev/badge/skills/sonature-lab/timsquad/inspect.svg" alt="Measured on agentmods" height="20"></a>
Per session 205 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,265 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00205 $0.01265
Opus 5 $0.00102 $0.00633
Sonnet 5 $0.00041 $0.00253
Haiku 4.5 $0.00020 $0.00127

Measured 5d ago against content hash e44dd060f3e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

inspect 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/count-hooks.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/inspect/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/inspect — TimSquad 프레임워크 건강 점검

릴리스 전, 대규모 작업 후, 또는 "뭔가 이상하다" 싶을 때 실행하는 종합 진단. 문서 drift와 데드코드는 시간이 지나면 반드시 누적된다 — 정기적으로 제거해야 파이프라인이 건강하다.

Protocol

  1. Gate 실행: npm run build + npm test — 하나라도 실패하면 즉시 FAIL 보고
  2. 7영역 자동 점검: 아래 영역을 병렬 Agent로 분산 실행
  3. RAG 리포트 생성: 영역별 Green/Amber/Red + 구체적 항목
  4. 권고 제시: 수정 방법과 우선순위 (Red > Amber)
  5. 리포트 저장: docs/inspect-report-{date}.md

점검 7영역

상세 체크리스트는 references/checklist.md를 Read하여 참조.

1. Hook 정합성

settings.json에 등록된 Hook 커맨드 vs scripts/ 실제 파일 대조.

  • 유령 Hook (등록됐지만 파일 없음)
  • 고아 스크립트 (파일 있지만 미등록)
  • Fail 전략 (|| true 유무) 의도 확인

실행: bash ${CLAUDE_SKILL_DIR}/scripts/count-hooks.sh

2. 스킬 정합성

templates/base/skills/ 전수 검증.

  • 고아 디렉토리 (SKILL.md 없음)
  • Frontmatter 누락 (name/description)
  • 120줄 초과 (Progressive Disclosure 위반)
  • references/ 포인터 끊김
  • BASE_SKILLS/SKILL_PRESETS/DOMAIN_SKILL_MAP 미등록 + methodology 매핑 확인

3. CLI 정합성

src/index.ts 등록 vs src/commands/*.ts 파일 대조.

  • 미등록 커맨드 파일
  • 유령 import
  • dist/ 빌드 동기화 (src 대비 dist 타임스탬프)

4. 문서 Drift

docs/competitive-analysis, MEMORY.md의 수치 주장 vs 실제 대조.

  • Hook 수, 스킬 수, 테스트 수, CLI 수
  • 보완계획 상태 (이슈 #31)
  • 내부 자기 불일치 (같은 문서 내 다른 수치)

5. 테스트 커버리지 갭

src//*.ts 소스 파일 대비 tests//*.test.ts 매핑.

  • 테스트 없는 핵심 소스 (commands/, lib/, daemon/)
  • utils/ 전수 미커버 여부

6. 설정 일관성

package.json, tsconfig.json, src/types/config.ts 교차 검증.

  • package.json version vs getInstalledVersion()
  • package.json files 필드 누락
  • npm scripts (test, build, prepublishOnly)
  • tsconfig strict 설정

7. 의존성 위생

코드 간 의존 관계 + 타입 export 검증.

  • 순환 import 탐지 (src/ 내부)
  • 미사용 export (types/ 내 타입이 src/ 어디에서도 안 쓰임)
  • 미사용 devDependencies

RAG 판정 기준

등급 기준
Green 자동 검증 통과, gate 이상 없음
Amber 기능 영향 없지만 drift 또는 갭 존재 — 권고 수정
Red 빌드/테스트 실패, 유령 참조, 심각한 불일치 — 즉시 수정

리포트 형식

# Inspect Report {date}

## Gate Results
| Gate | Status |
|------|--------|

## Summary
| 영역 | 판정 | 항목 수 |
|------|:----:|--------|

## 상세
### 1. Hook 정합성 — {판정}
...
### 7. 의존성 위생 — {판정}
...

## 권고 (우선순위순)
1. [Red] ...
2. [Amber] ...

Read the full file on GitHub · 122 lines

Files

What ships with it

2 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.

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. 5d ago First seen · 122 lines · 205 tokens per session scan A e44dd060f3e2

Subscribe to this mod's changes

inspect is a skill published in the GitHub repository sonature-lab/timsquad (11 stars, last pushed 5d ago), licensed MIT. It adds 205 tokens to every session and 1,265 once invoked, about $0.0010 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens