dify-a2a-plugin CLAUDE.md

A set of development instructions for a Dify plugin that lets AI agents find, call, and manage other agents through the Agent-to-Agent protocol. Dify is a platform for building and running AI applications and agents.

In plain words
What is it for?
Developing and testing the plugin, communicating with remote agents through JSON-RPC, and creating an installable Dify package.
Why use it?
It explains how to install dependencies, run tests, package the plugin, and account for the Python version used in production.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/flyryan/dify-a2a-plugin/claude-md
Clone the repo
git clone --depth 1 https://github.com/flyryan/dify-a2a-plugin
Per session 3,363 This file is loaded in full into every session.
When invoked 3,363 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.03363 $0.03363
Opus 5 $0.01682 $0.01682
Sonnet 5 $0.00673 $0.00673
Haiku 4.5 $0.00336 $0.00336

Measured 2d ago against content hash 8c3abf02bd36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dify-a2a-plugin CLAUDE.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

@patch('requests.post')
CLAUDE.md · 372 lines

How it starts

The opening of the file, as written. The whole thing — 372 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

This is a Dify plugin that implements the Agent-to-Agent (A2A) protocol, allowing Dify agents to communicate with and delegate tasks to external agents. The plugin provides tools for discovering, calling, and managing remote agents through JSON-RPC 2.0.

Development Commands

Plugin Development and Testing

# Install Python dependencies
# Note: Manifest requires Python 3.12, but newer versions may work in development
python3 -m venv .venv
source .venv/bin/activate  # On Mac/Linux
pip install -r requirements.txt

# Run unit tests
python3 -m unittest tools/tests/test_a2a_registry.py

# Build the plugin package (creates .difypkg file)
dify plugin package

# Install the Dify CLI (if not already installed)
brew tap langgenius/dify
brew install dify

Important Notes:

  • Manifest specifies Python 3.12 as runtime requirement
  • Local development may work with newer Python versions (e.g., 3.14)
  • Production deployment in Dify will use Python 3.12 as specified in manifest

Local Testing with Dify Plugin Runtime

For testing with the actual Dify plugin runtime environment:

  1. Using Dify CLI debug mode:

    dify plugin start --debug
    
  2. With dify-plugin-daemon (if available locally):

    • dify-plugin-daemon is not included in this repository (gitignored)
    • It's a local reference copy of the Dify plugin runtime
    • See Dify documentation for setting up local daemon

Architecture Overview

Plugin Structure

This is a Tool Provider Plugin that exposes 5 tools for A2A protocol operations:

  1. list_agents - Lists all available agents from the registry
  2. get_agent_capabilities - Fetches agent card from /.well-known/agent-card.json (fallback to agent.json)
  3. call_agent - Synchronous agent invocation via message/send JSON-RPC method
  4. submit_task - Asynchronous task submission via message/stream with SSE (extracts taskId from first event)
  5. get_task_status - Check status of async tasks via tasks/get JSON-RPC method

Read the full file on GitHub · 372 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. 2d ago First seen · 372 lines · 3,363 tokens per session scan A 8c3abf02bd36

Subscribe to this mod's changes

dify-a2a-plugin CLAUDE.md is an instructions file published in the GitHub repository flyryan/dify-a2a-plugin (11 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 3,363 tokens to every session, about $0.0168 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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

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 · 5,182 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 · 4,345 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

next.js 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