a2a

a2a is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 435 tokens per session (3,972 once invoked), scanned A, a copy of a2a, MIT.

A pattern for agents to discover, contact, and delegate work to other agents using shared communication rules. A2A means agent-to-agent communication.

In plain words
What is it for?
Building agent networks, discovering available agents, advertising their capabilities, and sending sub-tasks to specialist or remote agents.
Why use it?
It avoids tying a system to fixed agent addresses or one vendor, making cooperation possible across separate services, teams, or organizations.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Building agent networks, discovering available agents, advertising their capabilities, and sending sub-tasks to specialist or remote agents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hajekim/agentic-design-patterns-extension/a2a
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.

Any agent
npx skills add hajekim/agentic-design-patterns-extension --skill a2a
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extension

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/a2a.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/a2a)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/a2a"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/a2a.svg" alt="Measured on agentmods" height="20"></a>
Per session 435 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,972 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00435 $0.03972
Opus 5 $0.00217 $0.01986
Sonnet 5 $0.00087 $0.00794
Haiku 4.5 $0.00044 $0.00397

Measured 7d ago against content hash 98a9ff9dc5db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

a2a 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 7d 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.

response = requests.get(f"{self.agent_url}/.well-known/agent.json", timeout=10)
Origin

This is a copy

100% identical to a2a — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/a2a/SKILL.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-to-Agent (A2A) Communication Pattern

Overview

The Agent-to-Agent (A2A) Communication Pattern enables autonomous agents to discover, communicate with, and delegate tasks to other agents using standardized protocols. Just as MCP standardizes tool integration, A2A standardizes how agents interact with each other — enabling federated, interoperable multi-agent systems across organizational and technical boundaries.

Core Principle: Agents should be first-class collaborators, not just tool callers — standardize how agents discover and communicate with each other.

When This Skill Applies

Activate this pattern when:

  • Multiple specialized agents need to collaborate across service boundaries
  • Agents from different organizations or teams must interoperate
  • Dynamic agent discovery is needed (don't hardcode agent endpoints)
  • Complex tasks require delegating sub-tasks to expert agents
  • You want to compose existing agents into new workflows without rewriting them
  • Agent capabilities need to be advertised and discoverable programmatically

Rule of thumb: Use A2A when your multi-agent system spans organizational boundaries, requires dynamic discovery, or must be interoperable with third-party agents.

A2A Architecture

Key Concepts

  • Agent Card: Machine-readable capability advertisement (what the agent can do)
  • Task: The unit of work delegated between agents
  • Artifact: Output produced by an agent for the requesting agent
  • Discovery: Finding agents by capability, not by hardcoded URL
  • Trust: Authentication and authorization between agents

A2A Communication Flow

Agent A (Client)                          Agent B (Server)
     │                                          │
     │──── Discover Agent Cards ──────────────►│
     │◄─── Agent Card (capabilities) ──────────│
     │                                          │
     │──── Send Task (with context) ──────────►│
     │◄─── Task Acknowledgment ────────────────│
     │                                          │
     │──── Poll for status ───────────────────►│
     │◄─── Status Update ──────────────────────│
     │                                          │
     │──── Get Result ────────────────────────►│
     │◄─── Artifact (result) ──────────────────│

Read the full file on GitHub · 440 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. 7d ago First seen · 440 lines · 435 tokens per session scan A 98a9ff9dc5db

Subscribe to this mod's changes

a2a is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 435 tokens to every session and 3,972 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to a2a, differing in 3 lines, and is treated as a copy.