Borrowing it
Nothing to install: this file belongs to hollobit/assembly-api-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hollobit/assembly-api-mcp/main/.claude/skills/assembly-orchestrator/SKILL.mdgit clone --depth 1 https://github.com/hollobit/assembly-api-mcpWrote 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/hollobit/assembly-api-mcp/assembly-orchestrator)<a href="https://agentmods.dev/skills/hollobit/assembly-api-mcp/assembly-orchestrator"><img src="https://agentmods.dev/badge/skills/hollobit/assembly-api-mcp/assembly-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00565 |
| Opus 5 | $0.00016 | $0.00282 |
| Sonnet 5 | $0.00006 | $0.00113 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
assembly-orchestrator 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 8d 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.
What it actually says
Assembly Orchestrator Skill
MCP 도구 개선의 전체 워크플로를 조율합니다: 분석 → 설계 → 승인 → 구현 → 검증 → 배포.
트리거
- "MCP 도구를 개선해줘"
- "API 커버율을 높여줘"
- "새 API를 통합해줘"
- "도구 구조를 최적화해줘"
워크플로
Phase 1: 분석 (api-analyst)
└── 현황 파악 → 갭 분석 → 통합 기회 도출
Phase 2: 설계 (tool-designer)
└── 파라미터 스키마 → description → Lite/Full 배분
Phase 3: 승인
└── 사용자에게 설계 제안 → 승인 대기
Phase 4: 구현 (mcp-developer)
└── 코드 작성 → 빌드 → 테스트
Phase 5: 검증
└── Eval 실행 → 성능 벤치마크 → 보안 검토
Phase 6: 배포
└── 문서 동기화 → 커밋 → fly deploy → npm publish
실행 규칙
- 모든 에이전트는
model: opus사용 - 중간 산출물은
_workspace/디렉토리에 저장 - 각 Phase 완료 후 사용자에게 진행 상황 보고
- Phase 3 (승인)은 반드시 사용자 확인 후 진행
- Breaking change가 있으면 버전업 필수 (기억: feedback_breaking_change)
- 문서 동기화 필수 (기억: feedback_doc_sync)
사전 점검
실행 전 반드시 확인:
docs/discovered-all-codes.json존재 여부docs/tool-mapping.md최신 여부npm test통과 여부- git working tree clean 여부
산출물
| Phase | 파일 | 내용 |
|---|---|---|
| 1 | _workspace/analysis-{date}.md |
API 분석 보고서 |
| 2 | _workspace/design-{date}.md |
도구 설계 제안서 |
| 4 | _workspace/impl-{date}.md |
구현 변경 요약 |
| 5 | .claude/evals/v{ver}-eval.md |
Eval 보고서 |
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.
- 8d ago First seen · 65 lines · 32 tokens per session scan A dcf28ca17b51
assembly-orchestrator is a skill published in the GitHub repository hollobit/assembly-api-mcp (89 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 565 once invoked, about $0.0002 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 skills, from other repositories
scalar-design-system
Scalar's design system — design tokens, theming (@scalar/themes), CSS variables, and the @scalar/components library. Use when designing or implementing Scalar UI, especially with Paper (code-to-design / design-to-code), so output matches real Scalar tokens, colors, typography, spacing, and components instead of…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
fastapi-expert
Expert-level FastAPI development for high-performance Python APIs with async support. Use when the user mentions Python, API, async, REST, OpenAPI, or Pydantic, or when the task involves FastAPI Features.
openapi-expert
Expert-level OpenAPI/Swagger specification for API design, documentation, and code generation. Use when the user mentions swagger, API specs, REST, API design, or documentation, or when the task involves OpenAPI Specification, Webhooks, or Polymorphism.
jentic-api-scorecard
Use the @jentic/api-scorecard-cli to score an OpenAPI document against the Jentic API AI Readiness Framework (JAIRF). Use this skill whenever the user wants to score, grade, lint, or assess the AI-readiness / agent-readiness / quality of an OpenAPI (Swagger) spec — by local file or URL — or asks how to run the…