What is mcp-task CLAUDE.md?

A project guide for Claude Code, an AI coding assistant, describing an MCP server for running long-running AI tasks. It documents the project structure, development commands, building, testing, and code checks.

It is for developing, building, running, linting, type-checking, and testing the mcp-task project.

It gives the coding assistant the repository context needed to work with the project and its commands. It also records how to build and verify the code.

mcp-task CLAUDE.md — Instructions file for coding agents by just-every: A project guide for Claude Code, an AI coding…

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/just-every/mcp-task/claude-md

Clone the repo

git clone --depth 1 https://github.com/just-every/mcp-task

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/just-every/mcp-task/claude-md.svg)](https://agentmods.dev/instructions/just-every/mcp-task/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/just-every/mcp-task/claude-md"><img src="https://agentmods.dev/badge/instructions/just-every/mcp-task/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,169 This file is loaded in full into every session.

When invoked 1,169 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.01169	$0.01169
Opus 5	$0.00584	$0.00584
Sonnet 5	$0.00234	$0.00234
Haiku 4.5	$0.00117	$0.00117

Measured 3d ago against content hash da5e65ffc73d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-task CLAUDE.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Command line execution via child_process

CLAUDE.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 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.

Project Overview

An MCP server for running long-running AI tasks using the @just-every/task package. It provides a flexible interface for executing complex AI workflows with configurable models, context, and integrated search/command tools.

Core Modules & Files

src/serve.ts: MCP server implementation with task execution logic
src/index.ts: CLI entry point for standalone usage
src/utils/logger.ts: Logging utilities for debugging
bin/mcp-task.js: Executable entry point for npm package

Commands

Development

npm run serve:dev              # Run MCP server in development mode
npm run dev                    # Run CLI in development mode

Build & Production

npm run build                  # Compile TypeScript to JavaScript
npm run start                  # Run compiled CLI
npm run serve                  # Run compiled MCP server

Code Quality

npm run lint                   # Run ESLint
npm run typecheck             # TypeScript type checking
npm test                      # Run tests with Vitest

Architecture

This is a TypeScript-based MCP server that integrates with the @just-every/task package to run long-running AI tasks with various models and tools.

Core Components

MCP Server (src/serve.ts):
- Uses @modelcontextprotocol/sdk for MCP protocol
- Implements run_task tool for task execution
- Handles model selection and configuration
- Integrates search tools and command execution
Task Execution:
- Uses @just-every/task for AI task management
- Supports model classes (reasoning, standard, vision, fast)
- Supports specific model names (gpt-4.1, claude-3.5, etc.)
- Custom model registration for unknown models
Tool Integration:
- Search tools from @just-every/search
- Command line execution via child_process
- Extensible tool system

Read the full file on GitHub · 179 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.

3d ago First seen · 179 lines · 1,169 tokens per session scan A da5e65ffc73d

Subscribe to this mod's changes

mcp-task CLAUDE.md is an instructions file published in the GitHub repository just-every/mcp-task (5 stars, last pushed 29d ago), licensed MIT. It adds 1,169 tokens to every session, about $0.0058 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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).

microsoft/vscode · 6,785 tokens

mcp-task CLAUDE.md