mcp-devtools-server CLAUDE.md

Project instructions for an MCP DevTools server, a Node.js and TypeScript service that gives AI assistants standard development tools. They document the repository and its specialised agents and commands.

In plain words
What is it for?
Use them when working on the repository’s Python tools, quick fixes, issue triage or pull-request reviews, including the stated testing and quality checks.
Why use it?
They provide shared rules for implementing changes, fixing small bugs, reviewing code and managing issues in that project.

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/rshade/mcp-devtools-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/rshade/mcp-devtools-server
Per session 9,702 This file is loaded in full into every session.
When invoked 9,702 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 $0.09702 $0.09702
Opus 5 $0.04851 $0.04851
Sonnet 5 $0.01940 $0.01940
Haiku 4.5 $0.00970 $0.00970

Measured 3d ago against content hash 0c697058247a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-devtools-server 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.

CLAUDE.md · 1,240 lines

How it starts

The opening of the file, as written. The whole thing — 1,240 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

This is an MCP (Model Context Protocol) DevTools server project built with Node.js/TypeScript. The server provides standardized development tool integration for AI assistants.

Current Work: See GitHub Issues and Milestones for active development priorities.

Specialized Agents Available

This project has custom agents in .claude/ for common tasks. Use these instead of implementing manually:

Implementation Agents

/implement-python-tool [issue-number]

  • Implements Python tools from Epic #131
  • Follows Go tools pattern with cache optimization
  • Enforces 85-90%+ test coverage
  • Runs all quality gates

/quick-fix [issue-number]

  • Fast bug fixes (<1 hour, <50 lines)
  • Best for linting errors, test failures, docs
  • Rejects complex issues

Issue Management

/triage-issues [filter]

  • Categorizes and labels issues using gh issue list/view/edit
  • Assigns priorities (P0-P3)
  • Detects duplicates and stale issues
  • Filters: all, unlabeled, stale, P1

Code Review

/review-pr [pr-number] [--fix]

  • Deep review across 5 dimensions (correctness, security, performance, maintainability, best practices)
  • Uses gh pr view/diff/checks
  • Optional: implements fixes with --fix flag
  • Enforces quality gates

When to use agents:

  • ✅ Implementing Python tools (issues #132-144)
  • ✅ Quick bug fixes
  • ✅ Issue triage before sprint planning
  • ✅ Comprehensive PR reviews

See .claude/README.md for complete documentation.

Build and Test Commands

You can use either make commands (recommended) or npm scripts directly. Makefile is a thin wrapper around npm - npm is the source of truth.

# View all available commands
make help

# Common commands
make install         # Install dependencies
make build           # Build TypeScript
make dev             # Start development server
make test            # Run tests
make lint            # Run all linters (TypeScript, Markdown, YAML)
make check           # Run all linters and tests
make all             # Complete CI pipeline (install, check, build)

# Or use npm scripts directly
npm install
npm run build
npm run dev
npm run lint
npm run lint:md
npm run lint:yaml
npm test
npm run clean

# Run single test file
npm test -- src/__tests__/tools/make-tools.test.ts

# Run tests matching a pattern
npm test -- --testNamePattern="make_lint"

Read the full file on GitHub · 1,240 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. 3d ago First seen · 1,240 lines · 9,702 tokens per session scan A 0c697058247a

Subscribe to this mod's changes

mcp-devtools-server CLAUDE.md is an instructions file published in the GitHub repository rshade/mcp-devtools-server (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 9,702 tokens to every session, about $0.0485 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.