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/blizzy78/mcp-task-manager/claude-mdgit clone --depth 1 https://github.com/blizzy78/mcp-task-managerWrote 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/blizzy78/mcp-task-manager/claude-md)<a href="https://agentmods.dev/instructions/blizzy78/mcp-task-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/blizzy78/mcp-task-manager/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 | $0.01196 | $0.01196 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
mcp-task-manager 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 3d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Manager MCP Server
What the Project is About
The Task Manager MCP Server is a TypeScript-based Model Context Protocol (MCP) server that provides task management capabilities for AI agents and automation systems. This project implements an MCP server that exposes tools for structured task orchestration: task creation, task decomposition, and task status management.
The primary purpose of this project is to enable AI agents and other MCP clients to:
- Create and organize tasks in hierarchical structures with dependencies
- Decompose complex tasks into smaller, more manageable subtasks with sequence ordering
- Track task progression through defined states (todo, in-progress, done, failed)
- Orchestrate workflows with proper dependency validation and critical path tracking
The server maintains tasks in memory during execution and provides transport modes (STDIO, SSE, HTTP) for different integration scenarios.
MCP Specification Compliance
This server adheres to the Model Context Protocol (MCP) specification dated 2025-06-18. For full details, see the official specification:
- MCP Specification (2025-06-18): https://modelcontextprotocol.io/specification/2025-06-18
High Level View of the Architecture
The Task Manager MCP Server follows a straightforward architecture built on the Model Context Protocol (MCP) SDK:
Core Components
1. Server Infrastructure
- Entry Point (
index.ts): Routes between different transport modes based on command-line arguments - Server Factory (
task_manager.ts): Creates and configures the MCP server with tool handlers - Transport Modes:
- STDIO Mode (
stdio.ts): Standard input/output communication (default) - SSE Mode (
sse.ts): Server-Sent Events with Express.js for web integration - HTTP Mode (
streamableHttp.ts): HTTP-based communication
- STDIO Mode (
2. Task Management Tools
Discrete MCP tools provide the core functionality:
create_task: Creates new tasks with optional dependencies and uncertainty areasdecompose_task: Decomposes complex tasks into smaller, more manageable subtasks with sequence orderingupdate_task: Manages task lifecycle states with validation rules (todo, in-progress, done, failed)task_info: Returns full details for requested taskscurrent_task: Returns a list of tasks that are currently in progress (single agent mode only)
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.
- 3d ago First seen · 112 lines · 1,196 tokens per session scan A 5aed5c623091
mcp-task-manager CLAUDE.md is an instructions file published in the GitHub repository blizzy78/mcp-task-manager (4 stars, last pushed 12mo ago), licensed MIT. It adds 1,196 tokens to every session, about $0.0060 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
mcp-elicit CLAUDE.md
Claude Code instructions for blizzy78/mcp-elicit, covering elicitation mcp server, project description, high-level architecture, transport layer architecture and tool architecture.
braindb CLAUDE.md
Instructions for dimknaf/braindb, covering braindb — claude instructions, ⚠ tool priority — read this first, it overrides habit, at the start of every session, 1. get always-on rules (behavioral guidelines) and project structure.
gsd-task-manager CLAUDE.md
Instructions for vscarpenter/gsd-task-manager, covering claude.md, project overview, design context, core commands and development.
sonarqube-mcp-server AGENTS.md
AGENTS.md instructions for SonarSource/sonarqube-mcp-server, covering sonarqube mcp server, principles, prerequisites, build & verify and code style.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).
onplana-mcp-server GEMINI.md
Instructions for Onplana/onplana-mcp-server, covering onplana, gemini context, what onplana is, authenticating, hints when working with onplana data and common workflows.