agentmods.dev

mcp-devtools CLAUDE.md

Project instructions for MCP DevTools, a modular Go server that provides developer tools through a plugin-like architecture. They document commands for building, running, testing, linting, and managing dependencies.

In plain words
What is it for?
Use them when building or running the server, testing or linting changes, updating dependencies, or creating a new tool in its registry.
Why use it?
They give coding assistants the repository’s expected commands and explain where to read before changing the server or adding a new tool.

Instructions file

159 yesterday A scan 2,867 tokens original Apache-2.0
View the source file sammcj/mcp-devtools
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/sammcj/mcp-devtools/claude-md
Clone the repo
git clone --depth 1 https://github.com/sammcj/mcp-devtools
Per session 2,867 This file is loaded in full into every session.
When invoked 2,867 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 $0.02867 $0.02867
Opus 5 $0.01434 $0.01434
Sonnet 5 $0.00573 $0.00573
Haiku 4.5 $0.00287 $0.00287

Measured yesterday against content hash a70a02ea90f9, 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 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 yesterday.

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 · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 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.

Commands

Build and Run

  • make build - Build the server binary to bin/mcp-devtools
  • make run - Build and run server with stdio transport (default)
  • make run-http - Build and run server with HTTP transport on port 18080

Testing

  • make test - Run all tests (includes external API tests, ~10s)
  • make test-fast - Run tests without external API calls (~7s)
  • make test-verbose - Show detailed per-test timing
  • make test-slow - Show slowest tests sorted by duration
  • go test -short -v ./tests/... - Run specific test suites

Code Quality

  • make lint - Run linting, formatting and modernisation checks

Dependencies

  • make deps - Install dependencies
  • make update-deps - Update dependencies
  • go mod tidy - Clean up go.mod

Architecture

This is a modular MCP (Model Context Protocol) server built in Go that provides developer tools through a plugin-like architecture.

Please read the README.md for more information, and docs/creating-new-tools.md for details on how to create new tools.

Core Components

  1. Tool Registry (internal/registry/) - Central registry that manages tool registration and discovery
  2. Tool Interface (internal/tools/tools.go) - Defines the interface all tools must implement
  3. Main Server (main.go) - MCP server that supports multiple transports (stdio, SSE, HTTP)

Tool Categories

Tools are organised into categories under internal/tools/, e.g:

  • internetsearch/ - Internet Search API integrations (web, image, news, video, local)
  • packageversions/ - Package version checking across ecosystems (npm, python, go, java, swift, docker, github-actions, bedrock, rust)
  • shadcnui/ - shadcn/ui component information and examples
  • think/ - Structured reasoning tool for AI agents
  • webfetch/ - Web content fetching and conversion to markdown
  • utils/ - Shared utilities for tools (e.g. proxy)
  • etc..

Read the full file on GitHub · 235 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. yesterday First seen · 235 lines · 2,867 tokens per session scan A a70a02ea90f9

Subscribe to this mod's changes

mcp-devtools CLAUDE.md is an instructions file published in the GitHub repository sammcj/mcp-devtools (159 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,867 tokens to every session, about $0.0143 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.

Code reviewData and AILLMTestingagenticaiclinecodingdevtools
Related

Other instructions, from other repositories

20x AGENTS.md

Instructions for peakflo/20x, covering agents.md — multi-agent architecture (implemented), agent model, database schema, architecture and adapter architecture.

peakflo/20x · 6,580 tokens

goal-flight AGENTS.md

Instructions for simonrowland/goal-flight, covering agent notes, goal flight routing, project commands (this repo), git workflow (this repo) and git-visible trigger hygiene.

simonrowland/goal-flight · 1,855 tokens

m2e CLAUDE.md

Instructions for sammcj/m2e, covering claude.md, project overview, core architecture, main components and key files.

sammcj/m2e · 1,004 tokens

goal-flight CLAUDE.md

Instructions for simonrowland/goal-flight, covering claude code notes and git-visible trigger hygiene.

simonrowland/goal-flight · 155 tokens

shua-labs AGENTS.md

Instructions for jmenzies722/shua-labs, covering agents, what shua labs is, brand constraints, architecture and testing requirements.

jmenzies722/shua-labs · 466 tokens

gnap CLAUDE.md

Instructions for farol-team/gnap, covering claude.md, what this repo is, architecture, key files and core protocol concepts.

farol-team/gnap · 564 tokens