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.
npx skills add vbcherepanov/a2abridge --skill a2a-bridgegit clone --depth 1 https://github.com/vbcherepanov/a2abridgeWrote 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.
[](https://agentmods.dev/skills/vbcherepanov/a2abridge/a2a-bridge)<a href="https://agentmods.dev/skills/vbcherepanov/a2abridge/a2a-bridge"><img src="https://agentmods.dev/badge/skills/vbcherepanov/a2abridge/a2a-bridge.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01083 |
| Opus 5 | $0.00038 | $0.00541 |
| Sonnet 5 | $0.00015 | $0.00217 |
| Haiku 4.5 | $0.00008 | $0.00108 |
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 8d 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.
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.
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.jsonand a unique URL. - Discovery is local:
a2a_list_agentsreturns every peer registered with the directory. - Conversations are tasks:
a2a_send_messagecreates a task on a peer; the peer replies viaa2a_complete_task(or anothera2a_send_messagewith the sametask_id). - Your incoming queue is
a2a_inbox. Hooks usually drain it for you before each prompt — but you should still calla2a_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.
- FYI / context (breaking change in adjacent project, schema change, infra notice) → mention it in your reply to the user, then
- Address the user's prompt last. If a peer's FYI changes what you should do, fold it into the response.
Outbound flow — proactive
Send a message to peers without being asked when your change is about to surprise them. Triggers:
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.
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.
- 8d ago First seen · 78 lines · 76 tokens per session scan A 58de219142f2
a2a-bridge is a skill published in the GitHub repository vbcherepanov/a2abridge (11 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 1,083 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
telegram-agent
Telegram CLI for AI agents. Use when the user needs to read or search Telegram, send or edit a message, download media, organise Saved Messages, monitor conversations, or automate a Telegram task. Triggers on “check my messages”, “send a message”, “search Telegram”, “read unread”, “listen to chat”, “download from…
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
test-coverage
Use after writing tests to assess coverage quality across structural, mutation, requirements, and API/integration dimensions; organized knowledge for choosing and interpreting coverage analyses.
create-skill
Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before…
do-competitively
Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis.
create-rule
Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create rule for this issue so it not appears again.