mcp-a2a-documentation: Instructions file for Claude Code

CLAUDE.md

mcp-a2a-documentation CLAUDE.md is an instructions file for Claude Code from martoc/mcp-a2a-documentation. It costs 2,059 tokens per session, scanned A, original, MIT.

A set of coding instructions for the mcp-a2a-documentation project. It describes the project, British English and type-safety rules, error handling, and code style.

In plain words
What is it for?
Use it when modifying, testing, or reviewing the A2A documentation server.
Why use it?
It makes the project’s development expectations explicit, helping agents produce changes that fit the existing codebase.

Instructions file for Claude Code

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

This is martoc/mcp-a2a-documentation's own configuration. It tells Claude Code how to work on mcp-a2a-documentation 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-a2a-documentation configures →

Reuse

Borrowing it

Nothing to install: this file belongs to martoc/mcp-a2a-documentation. 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/martoc/mcp-a2a-documentation/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/martoc/mcp-a2a-documentation

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-a2a-documentation CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/martoc/mcp-a2a-documentation/claude-md/github.svg)](https://agentmods.dev/instructions/martoc/mcp-a2a-documentation/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/martoc/mcp-a2a-documentation/claude-md"><img src="https://agentmods.dev/badge/instructions/martoc/mcp-a2a-documentation/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-a2a-documentation CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/martoc/mcp-a2a-documentation/claude-md"><img src="https://agentmods.dev/badge/instructions/martoc/mcp-a2a-documentation/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,059 This file is loaded in full into every session.
When invoked 2,059 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 $0.02059 $0.02059
Opus 5.5 $0.00824 $0.00824
Sonnet 5.5 $0.00412 $0.00412
Haiku 4.5 $0.00206 $0.00206

Measured 2mo ago against content hash 54d313465bff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-a2a-documentation 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 · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Instructions

This file contains instructions for Claude Code when working with the MCP A2A Documentation Server codebase.

Project Overview

This is an MCP (Model Context Protocol) server that provides search and retrieval tools for Agent2Agent (A2A) protocol documentation. It uses:

  • FastMCP for the MCP server framework
  • SQLite FTS5 for full-text search with BM25 ranking
  • Python-frontmatter for parsing markdown files with YAML frontmatter
  • Sparse Git checkout for efficient cloning of the documentation directory
  • One upstream source:

Code Principles

British English

  • Use British English in all code, comments, and documentation
  • Examples: "initialise" not "initialize", "colour" not "color"

Type Safety

  • All functions must have type hints
  • Use modern union syntax: str | None instead of Optional[str]
  • Run mypy in strict mode before committing

Error Handling

  • Use explicit error handling
  • Raise appropriate exceptions with descriptive messages
  • Never silently fail

Code Style

  • Follow PEP 8 guidelines
  • Maximum line length: 120 characters
  • Use ruff for linting and formatting
  • See CODESTYLE.md for detailed style guidelines

Development Workflow

Making Changes

  1. Before starting:

    • Ensure development environment is initialised: make init
    • Understand the existing code structure
  2. During development:

    • Write tests for new functionality
    • Update type hints as needed
    • Add docstrings following Google style
  3. Before committing:

    • Format code: make format
    • Run linter: make lint
    • Run type checker: make typecheck
    • Run tests: make test
    • Or run all checks: make build

Testing

  • Write tests using pytest
  • Place tests in tests/ directory
  • Mirror source structure in test files
  • Test both success and failure cases
  • Aim for high coverage (>80%)

Read the full file on GitHub · 277 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 · 277 lines · 2,059 tokens per session scan A 54d313465bff

Subscribe to this mod's changes

mcp-a2a-documentation CLAUDE.md is an instructions file published in the GitHub repository martoc/mcp-a2a-documentation (0 stars, last pushed 5d ago), licensed MIT. It adds 2,059 tokens to every session, about $0.0082 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-a2a-documentation CLAUDE.md compared with instructions from other repositories

mcp-a2a-documentation CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-a2a-documentation CLAUDE.mdmartoc/mcp-a2a-documentationInstructions file05d agoMITA2,059Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode