mcp-skill-server: Instructions file for Claude Code

CLAUDE.md

mcp-skill-server CLAUDE.md is an instructions file for Claude Code from jcc-ne/mcp-skill-server. It costs 710 tokens per session, scanned A, original, MIT.

Project instructions for an MCP skill server, a local tool for developing, checking, and running agent skills before deployment.

In plain words
What is it for?
Use it to install dependencies, run tests, start the server, create or validate skills, and load skills from a chosen directory.
Why use it?
It provides the commands and structure needed to test skills locally instead of repeatedly deploying them to try changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is jcc-ne/mcp-skill-server's own configuration. It tells Claude Code how to work on mcp-skill-server 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-skill-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jcc-ne/mcp-skill-server. 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/jcc-ne/mcp-skill-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jcc-ne/mcp-skill-server

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.

agentmods badge for mcp-skill-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jcc-ne/mcp-skill-server/claude-md/github.svg)](https://agentmods.dev/instructions/jcc-ne/mcp-skill-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jcc-ne/mcp-skill-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jcc-ne/mcp-skill-server/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.

agentmods 80×15 button for mcp-skill-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jcc-ne/mcp-skill-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jcc-ne/mcp-skill-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 710 This file is loaded in full into every session.
When invoked 710 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 $0.00710 $0.00710
Opus 5.5 $0.00284 $0.00284
Sonnet 5.5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 2mo ago against content hash 99df40e87e52, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-skill-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 2mo 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 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

MCP Skill Server is a local MCP (Model Context Protocol) server for developing and testing skills before deploying them to production agents. It allows rapid iteration on skills locally instead of the deploy → test → iterate cycle.

Commands

# Install dependencies
uv sync --dev

# Run tests
uv run pytest

# Run server with example skills
uv run mcp-skill-server examples/

# Run server with custom skills directory
uv run mcp-skill-server /path/to/skills

# Initialize a new skill (standalone command)
uv run mcp-skill-init ./path/to/skill -n "skill-name" -d "Description"

# Or use as subcommand
uv run mcp-skill-server init ./path/to/skill

# Validate a skill (standalone command)
uv run mcp-skill-validate ./path/to/skill

# Or use as subcommand
uv run mcp-skill-server validate ./path/to/skill

# Install with GCS output handler support
uv sync --extra gcs

Architecture

Core Components

  • server.py: MCP server entry point. Exposes four MCP tools: list_skills, get_skill, run_skill, refresh_skills. Uses stdio transport.

  • loader.py: Skill discovery and schema inference. Scans for */SKILL.md files, parses YAML frontmatter, and dynamically discovers commands/parameters by running --help on each skill's entry command.

  • executor.py: Runs skill commands as subprocesses. Detects output files in output/ directory or via OUTPUT_FILE: prefix in stdout.

  • models.py: Pydantic request/response models.

Plugin System

Two plugin types in plugins/:

Output Handlers - Process files generated by skills:

  • OutputHandler (base class): Abstract interface for processing output files
  • LocalOutputHandler: Default handler, just tracks local file paths
  • GCSOutputHandler: Optional, uploads to Google Cloud Storage (requires gcs extra)

Response Formatters - Customize MCP tool response formatting:

  • ResponseFormatter (base class): Abstract interface for formatting execution results
  • DefaultResponseFormatter: Default text-based formatter

Read the full file on GitHub · 87 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. 2mo ago First seen · 87 lines · 710 tokens per session scan A 99df40e87e52

Subscribe to this mod's changes

mcp-skill-server CLAUDE.md is an instructions file published in the GitHub repository jcc-ne/mcp-skill-server (1 stars, last pushed 6mo ago), licensed MIT. It adds 710 tokens to every session, about $0.0028 per session on Opus 5.5. 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

mcp-skill-server CLAUDE.md compared with instructions from other repositories

mcp-skill-server CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-skill-server CLAUDE.mdjcc-ne/mcp-skill-serverInstructions file16mo agoMITA710Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot
generative-ai-for-beginners AGENTS.mdmicrosoft/generative-ai-for-beginnersInstructions file124ktodayMITA2,981Codex, OpenCode