a2a-langgraph-boilerplate: Instructions file for Claude Code

CLAUDE.md

a2a-langgraph-boilerplate CLAUDE.md is an instructions file for Claude Code from mrgoonie/a2a-langgraph-boilerplate. It costs 980 tokens per session, scanned A, original, MIT.

Project instructions for a boilerplate that coordinates multiple AI agents, with a supervisor assigning work and combining their results.

In plain words
What is it for?
Building or modifying workflows where a supervisor plans tasks, delegates them to agents through the A2A protocol, and produces a combined answer.
Why use it?
They explain how the agent cluster, tool connections, and task delegation are intended to work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is mrgoonie/a2a-langgraph-boilerplate's own configuration. It tells Claude Code how to work on a2a-langgraph-boilerplate 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 a2a-langgraph-boilerplate configures →

Reuse

Borrowing it

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

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 a2a-langgraph-boilerplate CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mrgoonie/a2a-langgraph-boilerplate/claude-md"><img src="https://agentmods.dev/badge/instructions/mrgoonie/a2a-langgraph-boilerplate/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 980 This file is loaded in full into every session.
When invoked 980 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 $0.00980 $0.00980
Opus 5 $0.00490 $0.00490
Sonnet 5 $0.00196 $0.00196
Haiku 4.5 $0.00098 $0.00098

Measured 9d ago against content hash 2a085ea3a295, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

a2a-langgraph-boilerplate 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 9d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

This project is a boilerplate for developers who want to start building an AI agent cluster faster and more efficient.

Concept

  • Each AI agent cluster can have multiple AI agent crews (AI Crews)
  • Each AI crew can have multiple AI agent, leaded by a superviser (a default AI agent of an AI crew)
  • Each AI agent can call tools via MCP servers integration

How it works

  • A supervisor agent will receive input (prompt) from a user via API call, then create a detailed plan with its current capabilities (AI agents underneat and their tools)
  • Then request the AI agents to perform tasks via A2A protocol
  • Wait for all AI agents finish given tasks
  • Grab all the results, analyze and decide to assign more tasks to AI agents, or finish the plan
  • Synthesize the results and respond to user based on the original input prompt.

Example workflow:

  • Case 1: Simple Direct Response - User asks "hello" and supervisor decides to answer directly with a simple response. This requires no agent delegation and completes in a single workflow step.
  • Case 2: Multi-Agent Collaboration with Termination Control - User asks for travel advice about Nha Trang beach (Vietnam):
    1. Supervisor receives query and creates a task plan with clear termination conditions
    2. Supervisor delegates to agent 1 (connected to Search API MCP server) to find top attractions
    3. Supervisor delegates to agent 2 (connected to Search API MCP server) to research local cuisine
    4. Each agent responds with its findings in a single message back to supervisor
    5. Supervisor synthesizes all information into a final response
    6. Workflow terminates after supervisor's final response (enforced by message depth limit)

Core Features

  • Create & manage AI crews easily (with a default supervisor agent, add/remove AI agents)
  • Create & manage AI agents easily (add/remove MCP tools)
  • Create & manage MCP servers easily (supports Streamable HTTP transport only)
  • Create & manage conversations with AI crews / AI agents easily
  • Able to monitor all the activity logs of AI crews and AI agents easily
  • Expose API for frontend (nextjs) interaction (support streaming request)
  • Expose Swagger API Docs for frontend integration instructions

Read the full file on GitHub · 80 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. 9d ago First seen · 80 lines · 980 tokens per session scan A 2a085ea3a295

Subscribe to this mod's changes

a2a-langgraph-boilerplate CLAUDE.md is an instructions file published in the GitHub repository mrgoonie/a2a-langgraph-boilerplate (40 stars, last pushed 1y ago), licensed MIT. It adds 980 tokens to every session, about $0.0049 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.

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 · 5,153 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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens