assembly-api-mcp CLAUDE.md

assembly-api-mcp CLAUDE.md is an instructions file for Claude Code from hollobit/assembly-api-mcp. It costs 692 tokens per session, scanned A, original, MIT.

Project instructions that route different requests to specialized workflows and define where design documentation lives.

In plain words
What is it for?
Selecting workflows, requiring design work to follow design/DESIGN.md, and guiding tasks such as testing, planning, shipping, and documenting releases.
Why use it?
They help choose the right process for tasks such as bug investigation, code review, deployment, design work, or MCP integration.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

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 instructions/hollobit/assembly-api-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/hollobit/assembly-api-mcp

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 assembly-api-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hollobit/assembly-api-mcp/claude-md.svg)](https://agentmods.dev/instructions/hollobit/assembly-api-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hollobit/assembly-api-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hollobit/assembly-api-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 692 This file is loaded in full into every session.
When invoked 692 The same file — it is already loaded in full.
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 $0.00692 $0.00692
Opus 5 $0.00346 $0.00346
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 6d ago against content hash 2c186267fab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

assembly-api-mcp CLAUDE.md 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 6d 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.

CLAUDE.md · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill routing

When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized workflows that produce better results than ad-hoc answers.

Key routing rules:

  • Product ideas, "is this worth building", brainstorming → invoke office-hours
  • Bugs, errors, "why is this broken", 500 errors → invoke investigate
  • Ship, deploy, push, create PR → invoke ship
  • QA, test the site, find bugs → invoke qa
  • Code review, check my diff → invoke review
  • Update docs after shipping → invoke document-release
  • Weekly retro → invoke retro
  • Design system, brand → invoke design-consultation
  • Visual audit, design polish → invoke design-review
  • Architecture review → invoke plan-eng-review
  • Save progress, checkpoint, resume → invoke checkpoint
  • Code quality, health check → invoke health
  • MCP 도구 개선, API 통합, 도구 구조 분석 → invoke assembly-orchestrator
  • API 커버율 분석 → invoke analyze-mcp
  • 도구 코드 구현/수정 → invoke implement-mcp

Design files

  • Visual/site/brand work must use ./design/DESIGN.md as the source of truth.
  • External design references and generated design docs belong under ./design/, not ./docs/ or _workspace/.
  • docs/mcp-design-analysis.md is tool architecture analysis, not the canonical visual design file.

하네스: 국회 MCP 서버 개선

목표: assembly-api-mcp의 276개 API → MCP 도구 래핑 구조를 분석·최적화하고, 승인된 개선안을 구현한다

에이전트 팀:

에이전트 역할 파일
api-analyst 276개 API 구조 분석, 중복/연관 파악, 통합 기회 도출 .claude/agents/api-analyst.md
tool-designer MCP 도구 인터페이스 UX 분석, 토큰 효율 최적화, AI 클라이언트 관점 설계 .claude/agents/tool-designer.md
mcp-developer 승인된 개선안 TypeScript 구현, 테스트 작성 .claude/agents/mcp-developer.md

스킬:

스킬 용도 사용 에이전트
analyze-mcp API 구조 분석 + 도구 설계 제안 api-analyst, tool-designer
implement-mcp 도구 코드 구현/수정 mcp-developer
assembly-orchestrator 분석→설계→구현 전체 워크플로우 조율 전체

Read the full file on GitHub · 57 lines

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. 6d ago First seen · 57 lines · 692 tokens per session scan A 2c186267fab9

Subscribe to this mod's changes

assembly-api-mcp CLAUDE.md is an instructions file published in the GitHub repository hollobit/assembly-api-mcp (89 stars, last pushed 4mo ago), licensed MIT. It adds 692 tokens to every session, about $0.0035 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.