a2a-gateway

a2a-gateway is a skill for Claude Code, Codex from adolfousier/opencrabs. It costs 45 tokens per session (402 once invoked), scanned A, original, MIT.

A reference for connecting software agents so they can discover each other and exchange tasks. It uses the Agent-to-Agent protocol with JSON-RPC 2.0, a standard format for sending structured requests and responses.

In plain words
What is it for?
Use it to configure an OpenCrabs HTTP gateway, expose an agent description, send or manage remote tasks, authenticate requests, and support structured multi-agent debate.
Why use it?
It removes the need to invent a separate communication interface for each agent pair. Remote agents can discover capabilities, send work, check task status, or cancel tasks through defined endpoints.

Skill for Claude CodeCodex

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

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/adolfousier/opencrabs/a2a-gateway
Any agent
npx skills add adolfousier/opencrabs --skill a2a-gateway
Clone the repo
git clone --depth 1 https://github.com/adolfousier/opencrabs

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-gateway

README.md
[![agentmods](https://agentmods.dev/badge/skills/adolfousier/opencrabs/a2a-gateway.svg)](https://agentmods.dev/skills/adolfousier/opencrabs/a2a-gateway)
Your own site
<a href="https://agentmods.dev/skills/adolfousier/opencrabs/a2a-gateway"><img src="https://agentmods.dev/badge/skills/adolfousier/opencrabs/a2a-gateway.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 402 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 5.1 $0.00045 $0.00402
Opus 5 $0.00023 $0.00201
Sonnet 5 $0.00009 $0.00080
Haiku 4.5 $0.00005 $0.00040

Measured 7d ago against content hash ba5aa84db99f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

a2a-gateway 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 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.

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.

src/docs/reference/templates/skills/a2a-gateway/SKILL.md · 45 lines

What it actually says

A2A Gateway Reference

OpenCrabs exposes an A2A Protocol HTTP gateway for peer-to-peer agent communication.

What it does

Other A2A-compatible agents send tasks via JSON-RPC 2.0. OpenCrabs processes them using its full tool suite and returns results.

Endpoints

  • GET /.well-known/agent.json — Agent Card discovery (skills, capabilities)
  • POST /a2a/v1 — JSON-RPC 2.0 (message/send, tasks/get, tasks/cancel)
  • GET /a2a/health — Health check

Setup

Enable in ~/.opencrabs/config.toml:

[a2a]
enabled = true
bind = "127.0.0.1"
port = 18790

Bee Colony Debate

Multi-agent structured debate with knowledge-enriched context from QMD memory search. Configurable rounds, confidence-weighted consensus based on ReConcile (ACL 2024).

Tool: a2a_send

Param Required What
action Yes discover, send, get, cancel
url Yes Base URL of remote agent (e.g. http://127.0.0.1:18790)
message For send Text to send
task_id For get/cancel Task ID to check/cancel
context_id Optional Continue a conversation
api_key Optional Bearer token for authenticated endpoints
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 · 45 lines · 45 tokens per session scan A ba5aa84db99f

Subscribe to this mod's changes

a2a-gateway is a skill published in the GitHub repository adolfousier/opencrabs (927 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 402 once invoked, about $0.0002 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.