mcp: Instructions file for Claude Code

CLAUDE.md

mcp CLAUDE.md is an instructions file for Claude Code, Codex from mrlesmithjr/mcp. It costs 4,813 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP workspace that combines several MCP servers, shared Python tools, and generated plugin marketplaces. MCP servers are programs that provide tools or data to an AI agent.

In plain words
What is it for?
Working on the workspace, locating packages and shared libraries, maintaining Claude and Codex plugin files, and following its marketplace-generation workflow.
Why use it?
They give coding agents the project’s structure, generated-file rules, and plugin conventions. This reduces the risk of editing generated metadata or placing new tools in the wrong package.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: ${CLAUDE_PLUGIN_ROOT} variable, but also runs codex exec. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is mrlesmithjr/mcp's own configuration. It tells Claude Code and Codex how to work on mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to mrlesmithjr/mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mrlesmithjr/mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/mrlesmithjr/mcp

Made for: Claude Code, Codex.

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 mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mrlesmithjr/mcp/claude-md.svg)](https://agentmods.dev/instructions/mrlesmithjr/mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mrlesmithjr/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mrlesmithjr/mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,813 This file is loaded in full into every session.
When invoked 4,813 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.04813 $0.04813
Opus 5 $0.02406 $0.02406
Sonnet 5 $0.00963 $0.00963
Haiku 4.5 $0.00481 $0.00481

Measured 6d ago against content hash dded971513c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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 · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in the mcp uv workspace.

Status: ACTIVE Last Updated: 2026-07-20


What this repo is

A uv workspace that consolidates all personal MCP servers into a single lockfile, shared dev tooling, and a marketplace generator. Each tool lives under packages/ as a subtree-merged member.


Structure

mcp/
├── pyproject.toml              # Virtual workspace root (no distribution)
├── uv.lock                     # Single root lockfile (authoritative)
├── .claude-plugin/
│   └── marketplace.json        # GENERATED -- do not hand-edit
├── .agents/plugins/
│   └── marketplace.json        # GENERATED Codex marketplace -- do not hand-edit
├── packages/
│   ├── mcp-common/             # Shared library (mrlesmithjr-mcp-common); PyPI-ready
│   ├── weather-tools/          # mrlesmithjr-mcp-weather-tools
│   │   ├── .claude-plugin/
│   │   │   └── plugin.json     # GENERATED: Claude plugin metadata (no hooks field)
│   │   ├── .codex-plugin/
│   │   │   └── plugin.json     # GENERATED: Codex plugin metadata
│   │   ├── .mcp.json           # GENERATED: Claude Code MCP definition (runs hooks/run_server.sh)
│   │   └── hooks/
│   │       ├── hooks.json      # GENERATED: SessionStart hook wiring
│   │       ├── install_deps.sh # GENERATED: SessionStart venv installer
│   │       └── run_server.sh   # GENERATED: cold-start launcher
│   ├── ynab-tools/             # mrlesmithjr-mcp-ynab-tools (same layout)
│   │                           # ships NO launchagents/: the dashboard is opt-in
│   │                           # via `ynab dashboard install` (see below)
│   ├── homeops/, lawnops/      # launchagents/: plist templates (__HOME__) + ops
│   │                           # scripts, shipped in the plugin and auto-loaded
│   ├── contacts-tools/         # mrlesmithjr-mcp-contacts-tools (Google People API; ContactsManager/PyObjC retained but unwired)
│   └── ...                     # 14 packages total; the 13 plugins share this layout
├── scripts/
│   ├── gen_marketplace.py      # Reads packages/*/pyproject.toml, emits per-package files
│   └── install_launchagents.sh # Manual/dev re-install of all LaunchAgents from the checkout
└── dev/
    └── register_dev.py         # Registers <tool>-dev servers pointing at .venv/bin/

Read the full file on GitHub · 359 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. 6d ago First seen · 359 lines · 4,813 tokens per session scan A dded971513c2

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository mrlesmithjr/mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 4,813 tokens to every session, about $0.0241 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens