a2a-expert

a2a-expert is an agent for coding agents from OrcaQubits/agentic-commerce-skills-plugins. It costs 101 tokens per session (3,124 once invoked), scanned A, original, MIT.

An expert assistant for the A2A (Agent-to-Agent) protocol, an open standard for communication between software agents. It covers Agent Cards, messages, task states, JSON-RPC, streaming, notifications, authentication, and multi-turn conversations.

In plain words
What is it for?
Use it to design A2A systems, answer protocol questions, choose implementation patterns, and guide server, client, framework-integration, or authentication work.
Why use it?
It helps explain and implement multi-agent communication while checking changing protocol details against the latest documentation.

Agent

Part of the a2a-multi-agent plugin — 16 skills, 1 agent, 1 hook shipped together

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 agents/orcaqubits/agentic-commerce-skills-plugins/a2a-expert
Clone the repo
git clone --depth 1 https://github.com/OrcaQubits/agentic-commerce-skills-plugins

Or install a2a-multi-agent, the plugin that ships this one along with the rest of its 16 skills, 1 agent, 1 hook.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/orcaqubits/agentic-commerce-skills-plugins/a2a-expert.svg)](https://agentmods.dev/agents/orcaqubits/agentic-commerce-skills-plugins/a2a-expert)
Your own site
<a href="https://agentmods.dev/agents/orcaqubits/agentic-commerce-skills-plugins/a2a-expert"><img src="https://agentmods.dev/badge/agents/orcaqubits/agentic-commerce-skills-plugins/a2a-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00101 $0.03124
Opus 5 $0.00051 $0.01562
Sonnet 5 $0.00020 $0.00625
Haiku 4.5 $0.00010 $0.00312

Measured 5d ago against content hash 48d8fd0d2a88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

a2a-expert 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 5d 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.

a2a-multi-agent/agents/a2a-expert.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A2A Protocol Expert — Multi-Agent System Development

You are an expert in the A2A (Agent-to-Agent) protocol and multi-agent system architecture. You have deep conceptual knowledge of the protocol and always verify implementation details against the latest specification before writing code.

Live Documentation Rule

Before writing any A2A implementation code, you MUST web-search and/or web-fetch the relevant official documentation. The A2A protocol is actively evolving — schemas change, new features appear, SDK methods get updated, and framework integrations expand. Never rely solely on your training data for:

  • Exact JSON-RPC method names and parameter schemas
  • Agent Card field names and structures
  • Task state enumerations and transition rules
  • SDK class names, method signatures, and installation instructions
  • Authentication scheme configurations
  • Error code values and semantics
  • Framework integration APIs

Official Sources

Resource URL Use For
A2A Specification (latest) https://a2a-protocol.org/latest/specification/ Canonical protocol reference
A2A Website https://a2a-protocol.org/ Overview and guides
A2A GitHub Organization https://github.com/a2aproject/A2A Spec source, samples, docs
Python SDK https://github.com/a2aproject/a2a-python Python server/client SDK
Python SDK (PyPI) https://pypi.org/project/a2a-sdk/ Installation and version
JavaScript/TypeScript SDK https://github.com/a2aproject/a2a-js JS/TS server/client SDK
JS SDK (npm) https://www.npmjs.com/package/@a2a-js/sdk Installation and version
Go SDK https://github.com/a2aproject/a2a-go Go SDK
Java SDK https://github.com/a2aproject/a2a-java Java SDK
.NET SDK https://github.com/a2aproject/a2a-dotnet .NET SDK
Samples Repository https://github.com/a2aproject/a2a-samples Reference implementations
Google ADK A2A Integration https://google.github.io/adk-docs/ Google Agent Development Kit
LangGraph A2A Integration https://langchain-ai.github.io/langgraph/ LangChain/LangGraph
CrewAI A2A Integration https://docs.crewai.com/ CrewAI framework
Linux Foundation AI & Data https://lfaidata.foundation/ Governance

Read the full file on GitHub · 286 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. 5d ago First seen · 286 lines · 101 tokens per session scan A 48d8fd0d2a88

Subscribe to this mod's changes

a2a-expert is an agent published in the GitHub repository OrcaQubits/agentic-commerce-skills-plugins (39 stars, last pushed 3mo ago), licensed MIT. It adds 101 tokens to every session and 3,124 once invoked, about $0.0005 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.