A coordination guide for coding agents that lets separate agent sessions exchange messages using the A2A 1.0 communication standard.

It helps agents find other agents, check their inboxes, send updates, and continue conversations about shared coding work.

It removes the need to coordinate manually across projects and helps agents notice incoming requests or share important changes with peers.

a2a-bridge — Skill for Claude Code by vbcherepanov/a2abridge

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 vbcherepanov/a2abridge --skill a2a-bridge

Clone the repo

git clone --depth 1 https://github.com/vbcherepanov/a2abridge

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vbcherepanov/a2abridge/a2a-bridge/github.svg)](https://agentmods.dev/skills/vbcherepanov/a2abridge/a2a-bridge)

Your own site

<a href="https://agentmods.dev/skills/vbcherepanov/a2abridge/a2a-bridge"><img src="https://agentmods.dev/badge/skills/vbcherepanov/a2abridge/a2a-bridge/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vbcherepanov/a2abridge/a2a-bridge"><img src="https://agentmods.dev/badge/skills/vbcherepanov/a2abridge/a2a-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,135 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00076	$0.01135
Opus 5.5	$0.00030	$0.00454
Sonnet 5.5	$0.00015	$0.00227
Haiku 4.5	$0.00008	$0.00113

Measured 1mo ago against content hash a4d13fb174ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

a2a-bridge 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 1mo 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.

Origin

This is a copy

100% identical to a2a-bridge — 0 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-bridge/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

a2a-bridge — inter-agent protocol skill

You are part of a distributed team of AI coding agents. Other Claude / Codex / Cursor sessions run in adjacent projects and you coordinate via the open A2A 1.0 protocol over a local discovery service. Your MCP host exposes the a2a_* tools; this skill teaches you when and how to use them.

Mental model

Each peer is identified by an Agent Card on /.well-known/agent-card.json and a unique URL.
Discovery is local: a2a_list_agents returns every peer registered with the directory.
Every message is its own task: a2a_send_message creates a task on the peer, which stays working until the peer answers with a2a_complete_task. Continue a conversation with a new message that reuses the context_id of the previous task. Pass task_id only for a task that is waiting for input — A2A 1.0 rejects messages to a task that is still being worked on or already finished.
Your incoming queue is a2a_inbox. Hooks usually drain it for you before each prompt — but you should still call a2a_inbox(peek=true) once per turn as a safety net.

Self-label

You have a session-stable label of the form <basename-cwd>-<4hex> (e.g. a2abridge-3a2f). Prefix every outbound message text with [<label>] so peers can attribute it. Your inbox shows the sender's label the same way.

Inbound flow — every turn

Before answering the user, walk the inbox once:

a2a_inbox(peek=true) — peek so the hook's drain remains authoritative.
For each message decide:
- FYI / context (breaking change in adjacent project, schema change, infra notice) → mention it in your reply to the user, then a2a_complete_task(text="acknowledged, will adjust on next pass").
- Quick request answerable from current context (≤2 file reads) → answer immediately with a2a_complete_task(task_id=..., text=...).
- Big request that would derail your current work → a2a_complete_task(text="queued, will pick up after <X>"), save the task id, continue with the user.
Address the user's prompt last. If a peer's FYI changes what you should do, fold it into the response.

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/protocol.md 4.1 KB

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.

1mo ago Changed a4d13fb174ec
2mo ago First seen · 78 lines · 76 tokens per session scan A 58de219142f2

Subscribe to this mod's changes

a2a-bridge is a skill published in the GitHub repository vbcherepanov/a2abridge (16 stars, last pushed 6d ago), licensed MIT. It adds 76 tokens to every session and 1,135 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to a2a-bridge, differing in 0 lines, and is treated as a copy.

Building agents Claude Code a2a ai-agents cline codex-cli cursor

a2a-bridge next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
a2a-bridgevbcherepanov/a2abridge	Skill	16	6d ago	MIT	A	76	Claude Code
telegram-agentbeautyfree/telegram-agent	Skill	11	1mo ago	GPL-3.0	A	90	Claude Code, Codex
verifyyha9806/academic-writing-toolkit	Skill	54	11d ago	MIT	A	26	Claude Code
ainb-fleet:daemonstevengonsalvez/agents-in-a-box	Skill	27	9d ago	MIT	A	89	Claude Code
ainb-fleet:broadcaststevengonsalvez/agents-in-a-box	Skill	27	9d ago	MIT	A	114	Claude Code
calibration-technicianwonsukchoi/domain-experts	Skill	25	5d ago	MIT	A	112	Claude Code, Codex
aerospace-engineering-technicianwonsukchoi/domain-experts	Skill	25	5d ago	MIT	A	169	Claude Code, Codex