What is skill-mcp CLAUDE.md?

Guidance for an MCP server that lets language models manage skills, files, and environment variables through a small set of tools. MCP is a way for AI applications to call external tools.

It helps maintain tools for listing, creating, updating, deleting, and validating skills and files, managing environment variables, and running skill scripts.

It explains the project's layered design and keeps related operations organized instead of spreading them across many separate tools.

How fkesheh/skill-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to fkesheh/skill-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/fkesheh/skill-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/fkesheh/skill-mcp

Made for: Claude Code.

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/fkesheh/skill-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/fkesheh/skill-mcp/claude-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fkesheh/skill-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fkesheh/skill-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,893 This file is loaded in full into every session.

When invoked 1,893 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.

Model	Per session	Once invoked
Fable 5.1	$0.01893	$0.01893
Opus 5	$0.00946	$0.00946
Sonnet 5	$0.00379	$0.00379
Haiku 4.5	$0.00189	$0.00189

Measured 8d ago against content hash 6d3e6c47cdd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

skill-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 8d 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 · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 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

skill-mcp is a Model Context Protocol (MCP) server that enables LLMs to manage skills stored in ~/.skill-mcp/skills. The system uses a unified CRUD architecture to provide programmatic access to skill management, file operations, environment variables, and script execution.

Architecture

CRUD-Based Tool Design

The codebase recently underwent a major refactor to unify all operations into 3 main CRUD tools instead of 10+ individual tools:

skill_crud (src/skill_mcp/tools/skill_crud.py) - All skill operations (list, get, create, delete, validate)
skill_files_crud (src/skill_mcp/tools/skill_files_crud.py) - All file operations (read, create, update, delete) with bulk support
skill_env_crud (src/skill_mcp/tools/skill_env_crud.py) - All environment variable operations (read, set, delete, clear)
run_skill_script (src/skill_mcp/tools/script_tools.py) - Script execution only

Key principle: Tool descriptions should be clean and focused on functionality rather than implementation details. Avoid adding meta-commentary about "context window optimization" or comparing to old tools. AI talks with MCP through json, so examples need to be in json format.

Layered Architecture

MCP Server (server.py)
    ↓
CRUD Tools (tools/*.py) - Operation routing
    ↓
Services (services/*.py) - Business logic
    ↓
Utils (utils/*.py) - Helpers & validation

Services:

skill_service.py - Skill discovery, metadata parsing, validation
file_service.py - File CRUD with path security validation
env_service.py - Environment variable management with merge/replace modes
script_service.py - Script execution with PEP 723 dependency detection

Core modules:

core/config.py - All configuration constants (SKILLS_DIR, timeouts, limits)
core/exceptions.py - Custom exception hierarchy
models.py - Pydantic models for individual operations (backward compat)
models_crud.py - Unified CRUD input models (SkillCrudInput, SkillFilesCrudInput, SkillEnvCrudInput)

Read the full file on GitHub · 255 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.

8d ago First seen · 255 lines · 1,893 tokens per session scan A 6d3e6c47cdd5

Subscribe to this mod's changes

skill-mcp CLAUDE.md is an instructions file published in the GitHub repository fkesheh/skill-mcp (30 stars, last pushed 9mo ago), licensed MIT. It adds 1,893 tokens to every session, about $0.0095 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.

Building agents LLM ai claude-skills mcp-server

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 · 5,153 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

skill-mcp: Instructions file for Claude Code