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.
npx agentmods add instructions/adamwulf/mcp-template/claude-mdgit clone --depth 1 https://github.com/adamwulf/mcp-templateWrote 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.
[](https://agentmods.dev/instructions/adamwulf/mcp-template/claude-md)<a href="https://agentmods.dev/instructions/adamwulf/mcp-template/claude-md"><img src="https://agentmods.dev/badge/instructions/adamwulf/mcp-template/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00742 | $0.00742 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
mcp-template 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.
How it starts
The opening of the file, as written. The whole thing — 84 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.
Build and Test Commands
# Build the package
swift build
# Run tests
swift test
# Run the command line MCP server
swift run mcpexample run
# Format code using SwiftLint
./format-files.sh
# Build in Xcode (for iOS/macOS apps)
open MCPExample/MCPExample.xcworkspace
Architecture Overview
This repository provides a template for building MCP (Model Control Protocol) servers in Swift with three main components:
1. EasyMCP Library (Sources/EasyMCP/)
- Core MCP server implementation using the official
mcp-swift-sdk - Wraps the SDK to provide a simplified interface for registering tools and handling MCP communications
- Uses stdio transport for command-line MCP servers
- Key class:
EasyMCP- manages server lifecycle, tool registration, and MCP protocol handling
2. EasyMacMCP Library (Sources/EasyMacMCP/)
- Specialized implementation for macOS applications that need App Store compatibility
- Uses named pipes for inter-process communication between a sandboxed Mac app and a helper executable
- Enables MCP functionality in sandboxed environments where stdio access is restricted
- Key classes:
EasyMCPHost- Base class for managing pipe-based communication with helper processesMCPProtocols.swift- Protocol definitions for request/response communication- Pipe classes (
*Pipe.swift) - Handle reading/writing to named pipes
3. Command Line Example (Sources/mcpexample/)
- Demonstrates basic MCP server usage with
EasyMCP - Registers sample tools (
helloWorld,helloPerson,helloEveryone) - Shows how to handle tool registration, server startup, and graceful shutdown
- Uses
ArgumentParserfor CLI interface
4. macOS App Example (MCPExample/)
- Xcode workspace demonstrating App Store-safe MCP integration
- Main app uses
EasyMacMCPto communicate with a helper executable via named pipes - Helper executable (
mcp-helper) runs the actual MCP server usingEasyMCP - Shows how to build MCP functionality that works within macOS sandboxing restrictions
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.
- 6d ago First seen · 84 lines · 742 tokens per session scan A 335d5e23b63d
mcp-template CLAUDE.md is an instructions file published in the GitHub repository adamwulf/mcp-template (17 stars, last pushed 5d ago), licensed MIT. It adds 742 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
awesome-copilot-id AGENTS.md
AGENTS.md instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
llm-safe-haven CLAUDE.md
Claude Code instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
AGENTS.md instructions for kleosr/kleosrules, covering agents.md — repository agent handbook, law, pack, skills (on demand) and workflows.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
xtool CLAUDE.md
Instructions for 2389-research/xtool, covering xtool plugin, skills included, using-xtool (main skill), key patterns and xtool is not xcodegen.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.