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 instructions/deokgoo/task-manager-mcp/claude-mdgit clone --depth 1 https://github.com/deokgoo/task-manager-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/instructions/deokgoo/task-manager-mcp/claude-md)<a href="https://agentmods.dev/instructions/deokgoo/task-manager-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/deokgoo/task-manager-mcp/claude-md.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 | $0.03625 | $0.03625 |
| Opus 5 | $0.01813 | $0.01813 |
| Sonnet 5 | $0.00725 | $0.00725 |
| Haiku 4.5 | $0.00363 | $0.00363 |
Grade A, and why
task-manager-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 4d 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 — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
프로젝트 개요
MCP Task Master는 Trello 스타일의 단순하고 효율적인 작업 관리 도구입니다. 복잡한 LLM 의존적 기능을 제거하고, 순수한 MCP(Model Context Protocol) 기능에 집중하여 진정한 MCP의 효율성을 구현합니다.
🎯 핵심 특징
- 단순함: Trello 수준의 직관적인 CRUD 작업 관리
- 효율성: 19개 도구에서 11개 도구로 축소 (42% 감소)
- 순수 MCP: LLM 분석 대신 MCP 본연의 기능에 집중
- 이중 언어: 한국어/영어 지원
- 실시간 Dashboard: React 기반 웹 인터페이스
핵심 기술 스택
- 언어: TypeScript (ES Module)
- 런타임: Node.js 18+
- 주요 라이브러리:
@modelcontextprotocol/sdk: MCP 서버 구현express: 웹 서버 (Dashboard GUI)zod: 데이터 검증 및 스키마 정의uuid: 고유 ID 생성dotenv: 환경 변수 관리
빌드 및 개발 명령어
일반적인 개발 워크플로우
# 의존성 설치
npm install
# TypeScript 컴파일 및 빌드
npm run build
# 개발 모드 실행 (ts-node 사용)
npm run dev
# 프로덕션 실행
npm run start
# 테스트 실행
npm run test
# 테스트 커버리지
npm run test:coverage
특별한 빌드 과정
npm run build 명령어는 다음을 수행합니다:
- TypeScript 컴파일 (
tsc) - 템플릿 마크다운 파일들을 dist로 복사 (
copyfiles) - 정적 웹 파일들을 dist로 복사
- 실행 파일에 shebang 추가 (
node scripts/add-shebang.js)
프로젝트 아키텍처
핵심 디렉토리 구조
src/
├── index.ts # MCP 서버 진입점 및 11개 도구 등록
├── models/ # 단순화된 데이터 모델
│ └── taskModel.ts # Task 인터페이스 및 CRUD 함수들
├── messages/ # 다국어 메시지 시스템 🆕
│ ├── index.ts # 언어 감지 및 메시지 로더
│ ├── korean.ts # 한국어 메시지
│ └── english.ts # 영어 메시지
├── prompts/ # 템플릿 파일 저장 (최소화됨)
│ ├── loader.ts # 템플릿 로딩 시스템
│ └── templates_ko/ # 한국어 템플릿 (Dashboard용만 유지)
├── tools/ # 11개 MCP 도구 구현체
│ ├── task/ # 7개 핵심 작업 관리 도구
│ │ ├── listTasks.ts # 작업 목록 조회
│ │ ├── executeTask.ts # 단순화된 작업 실행 가이드
│ │ ├── deleteTask.ts # 작업 삭제
│ │ ├── clearAllTasks.ts # 전체 작업 삭제
│ │ ├── updateTask.ts # 작업 내용 수정
│ │ ├── queryTask.ts # 작업 검색
│ │ └── getTaskDetail.ts # 작업 상세 조회
│ └── dashboard/ # 6개 Dashboard 관리 도구
│ ├── startDashboard.ts # 대시보드 서버 시작
│ ├── stopDashboard.ts # 대시보드 서버 정지
│ ├── statusDashboard.ts # 대시보드 상태 확인
│ ├── listDashboardProjects.ts # 프로젝트 목록
│ ├── addDashboardProject.ts # 프로젝트 추가
│ └── createTasksInProject.ts # 프로젝트 작업 생성
├── types/ # 단순화된 타입 정의
│ └── index.ts # Task, TaskStatus 등 핵심 타입만 유지
├── utils/ # 공통 유틸리티
│ ├── agentMatcher.ts # AI Agent 매칭 로직
│ ├── fileLoader.ts # 파일 처리
│ ├── paths.ts # 경로 관리
│ └── regex.ts # 정규표현식 패턴
└── web/ # 웹 서버 (Dashboard용)
└── webServer.ts # Express 서버 구현
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.
- 4d ago First seen · 379 lines · 3,625 tokens per session scan A e37a3319485c
task-manager-mcp CLAUDE.md is an instructions file published in the GitHub repository deokgoo/task-manager-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 3,625 tokens to every session, about $0.0181 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).