just-mcp CLAUDE.md

just-mcp CLAUDE.md is an instructions file for coding agents from toolprint/just-mcp. It costs 3,858 tokens per session, scanned A, original, MIT.

Project instructions for just-mcp, a server that turns tasks from justfiles into tools an AI assistant can discover and run. A justfile is a plain-text file that defines reusable project commands.

In plain words
What is it for?
Use them when developing just-mcp, especially for setting up the project, running checks, building, testing, formatting, linting, and automating workflows.
Why use it?
They give the assistant the project's setup, build, test, formatting, linting, and pre-commit commands in one place. This reduces guesswork about how the repository should be worked on.

Instructions file

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/toolprint/just-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/toolprint/just-mcp

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 just-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/toolprint/just-mcp/claude-md.svg)](https://agentmods.dev/instructions/toolprint/just-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/toolprint/just-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/toolprint/just-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,858 This file is loaded in full into every session.
When invoked 3,858 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 $0.03858 $0.03858
Opus 5 $0.01929 $0.01929
Sonnet 5 $0.00772 $0.00772
Haiku 4.5 $0.00386 $0.00386

Measured 5d ago against content hash 2165156029ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

just-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 5d 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 · 484 lines

How it starts

The opening of the file, as written. The whole thing — 484 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

just-mcp is a Model Context Protocol (MCP) server that transforms justfiles into AI-accessible automation tools. It monitors directories for justfiles, parses them, and exposes their tasks as MCP tools that AI assistants can discover and execute.

Essential Development Commands

The justfile has been refactored into a modular system with specialized modules. Use these unified commands:

# Quick Start & Setup
just quickstart         # Complete setup for new developers
just dev-setup          # Comprehensive development environment setup
just help               # Comprehensive help system with discovery features

# Core Development Workflow
just build [mode]       # Build project (debug/release)
just test [coverage]    # Run tests (with optional coverage)
just format [target]    # Format code (rust/json/markdown/all)
just lint [target] [fix] # Lint code with optional auto-fix
just check [target]     # Combined format + lint + test (quick/full/all)
just pre-commit         # Full validation before committing

# Workflow Automation
just workflow quick     # Quick development workflow (format + lint + test)
just workflow full      # Full workflow with coverage and release build  
just workflow commit    # Commit-ready workflow (runs pre-commit)
just ci                 # Complete CI/CD checks locally

# Installation & Release
just install [features] # Install binaries (with optional vector-search)
just release-info       # Show release binary information
just clean              # Clean build artifacts

# Discovery & Navigation
just list               # List all recipes organized by groups
just groups             # List all recipe groups
just summary            # Compact recipe list
just help-topics        # Show all available help topics

Modular Justfile Architecture

The justfile has been transformed from a monolithic 870-line file into a modular system:

Read the full file on GitHub · 484 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. 5d ago First seen · 484 lines · 3,858 tokens per session scan A 2165156029ef

Subscribe to this mod's changes

just-mcp CLAUDE.md is an instructions file published in the GitHub repository toolprint/just-mcp (46 stars, last pushed 1y ago), licensed MIT. It adds 3,858 tokens to every session, about $0.0193 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.