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 agentmods add commands/dev-gom/claude-code-marketplace/analyzegit clone --depth 1 https://github.com/Dev-GOM/claude-code-marketplaceWhat 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 | $0.00011 | $0.02598 |
| Opus 5 | $0.00005 | $0.01299 |
| Sonnet 5 | $0.00002 | $0.00520 |
| Haiku 4.5 | $0.00001 | $0.00260 |
Grade A, and why
analyze 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 — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Project Status
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
⚠️ 커맨드 구분: 이것은 플러그인 커맨드 (/spec-kit:analyze)입니다. 정보 수집과 사용자 논의를 담당합니다. 실제 파일 생성/업데이트는 GitHub Spec-Kit CLI 커맨드 (/speckit.analyze)가 수행합니다.
🌐 언어 지시사항: 이 명령어를 실행할 때는 사용자의 시스템 언어를 자동으로 감지하여 해당 언어로 모든 안내, 질문, 분석 리포트, 출력을 제공해야 합니다. 시스템 환경 변수(LANG, LC_ALL 등)나 사용자의 이전 대화 패턴을 분석하여 언어를 판단하세요.
spec-kit 프로젝트의 전체 상태를 분석하고 진행 상황을 리포트합니다.
Purpose
다음을 파악합니다:
- 명세-계획-작업의 정합성
- 구현 진행률
- 헌법 준수 여부
- 차단 요소
- 다음 액션
Step 1: Gather Status
모든 spec-kit 파일 읽기:
# 현재 브랜치 확인
CURRENT_BRANCH=$(git branch --show-current)
# 헌법 (전역)
cat .specify/memory/constitution.md
# 기능별 파일들 (브랜치별)
cat "specs/$CURRENT_BRANCH/spec.md"
cat "specs/$CURRENT_BRANCH/plan.md"
cat "specs/$CURRENT_BRANCH/tasks.md"
Step 2: Analyze Completeness
각 문서의 완성도 평가:
Constitution
- ✅ 존재 / ❌ 없음
- Status: Draft / Approved
- 원칙 개수: [N]개
- 품질 게이트: [N]개
Specification
- ✅ 존재 / ❌ 없음
- Status: Draft / In Review / Approved
- User Stories: [N]개
- Acceptance Criteria: [N]개
- Open Questions: [N]개 (⚠️ 해결 필요)
Plan
- ✅ 존재 / ❌ 없음
- Status: Draft / Approved
- Phases: [N]개
- Open Technical Questions: [N]개 (⚠️ 해결 필요)
Tasks
- ✅ 존재 / ❌ 없음
- Total Tasks: [N]개
- Completed: [N]개 ([%]%)
- In Progress: [N]개
- Pending: [N]개
Step 3: Check Alignment
문서 간 정합성 확인:
Specification → Plan:
- 명세의 모든 요구사항이 계획에 반영되었는가?
- 계획의 기술 선택이 명세 제약사항을 만족하는가?
Plan → Tasks:
- 계획의 모든 Phase가 작업으로 분해되었는가?
- 작업 예상 시간의 합이 현실적인가?
Constitution → All:
- 명세가 헌법 원칙을 준수하는가?
- 계획이 기술 표준을 따르는가?
- 작업이 품질 게이트를 포함하는가?
Step 4: Identify Blockers
진행을 막는 요소 식별:
High Priority:
- 🔴 Open Questions 미해결
- 🔴 상충되는 요구사항
- 🔴 누락된 의존성
- 🔴 차단된 작업 (의존성 미완료)
Medium Priority:
- 🟡 명확하지 않은 요구사항
- 🟡 기술 스택 미결정
- 🟡 테스트 전략 없음
Low Priority:
- 🟢 문서 포맷팅
- 🟢 예제 부족
Step 5: Save Draft and Execute Spec-Kit Command
5.1 수집된 정보를 Draft 파일로 저장
먼저 현재 기능의 drafts 디렉토리 생성:
# drafts 디렉토리 생성
mkdir -p "specs/$CURRENT_BRANCH/drafts"
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 First seen · 331 lines · 11 tokens per session scan A e24cb1ac8fd2
analyze is a command published in the GitHub repository Dev-GOM/claude-code-marketplace (97 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 2,598 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.