a2a-multi-agent

An Agent-to-Agent system that lets AI agents discover one another, exchange tasks, and delegate work using a shared communication standard. It connects those tasks to XActions tools and can stream progress as work happens.

In plain words
What is it for?
Use it to expose an agent description, accept JSON-RPC tasks, delegate work to other agents, stream updates over SSE, send webhook notifications, and manage agent discovery and authentication.
Why use it?
Separate AI agents otherwise need custom integrations to find each other, pass tasks, track results, and authenticate communication. This provides the described bridge and task-management pieces in one setup.

Skill for Claude CodeCodex

Part of the XActions plugin — 47 skills, 1 command, 6 agents, 1 MCP server 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 skills/nirholas/xactions/a2a-multi-agent
Any agent
npx skills add nirholas/XActions --skill a2a-multi-agent
Clone the repo
git clone --depth 1 https://github.com/nirholas/XActions

Made for: Claude Code, Codex.

Or install XActions, the plugin that ships this one along with the rest of its 47 skills, 1 command, 6 agents, 1 MCP server.

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,890 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00100 $0.01890
Opus 5 $0.00050 $0.00945
Sonnet 5 $0.00020 $0.00378
Haiku 4.5 $0.00010 $0.00189

Measured 3d ago against content hash 92b762c189d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

a2a-multi-agent 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 3d 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.

curl http://localhost:3100/a2a/health
skills/a2a-multi-agent/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: A2A Multi-Agent Orchestration

Turn XActions into an A2A-compatible agent that can discover, communicate with, and delegate tasks to other AI agents using Google's Agent-to-Agent protocol.

When to Use

  • User wants to connect XActions with external AI agents
  • User needs multi-agent orchestration (decompose → delegate → aggregate)
  • User asks about A2A protocol, agent cards, or inter-agent communication
  • User wants to run the A2A server or manage agent discovery
  • User needs real-time task streaming between agents

Files

File Purpose
src/a2a/types.js Shared constants, factories, validators
src/a2a/skillRegistry.js MCP tool → A2A skill bridge
src/a2a/agentCard.js Agent Card generation (.well-known/agent.json)
src/a2a/taskManager.js Task lifecycle (create, transition, execute)
src/a2a/bridge.js A2A ↔ MCP translation layer + NLP
src/a2a/streaming.js SSE streaming for real-time updates
src/a2a/push.js Webhook push notifications
src/a2a/auth.js API key + JWT inter-agent auth
src/a2a/discovery.js Agent registry, skill matching, trust scoring
src/a2a/orchestrator.js Task decomposer + delegator + orchestrator
src/a2a/server.js Express HTTP server (port 3100)
src/a2a/index.js Barrel export + CLI commands + factory
dashboard/a2a.html Web dashboard for monitoring

Quick Start

Start the A2A server

# Via CLI
node src/a2a/server.js

# Directly
node src/a2a/server.js

# With session cookie for browser automation
node src/a2a/server.js --cookie "YOUR_X_SESSION_COOKIE"

Check health

curl http://localhost:3100/a2a/health

View Agent Card

curl http://localhost:3100/.well-known/agent.json

Send a task

curl -X POST http://localhost:3100/a2a/tasks \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tasks/send",
    "params": {
      "message": {
        "role": "user",
        "parts": [{"type": "text", "text": "get profile for @nichxbt"}]
      }
    },
    "id": "1"
  }'

Read the full file on GitHub · 198 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. 3d ago First seen · 198 lines · 100 tokens per session scan A 92b762c189d9

Subscribe to this mod's changes

a2a-multi-agent is a skill published in the GitHub repository nirholas/XActions (496 stars, last pushed 5d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,890 once invoked, about $0.0005 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.