A client for communicating with remote AI agents through A2A, a standard way for AI agents to exchange tasks and results. It first reads an agent's AgentCard, a document describing its abilities and connection details.

Use it to discover an A2A agent, send tasks, check task status, and retrieve results from a remote service.

It removes the need to manually discover an agent's interface and construct protocol requests. It also helps you inspect what an agent supports before sending work to it.

a2a-client — Skill for Claude Code and Codex by a2aproject: A client for communicating with remote AI agents through…

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/a2aproject/a2a-tck/a2a-client

Any agent

npx skills add a2aproject/a2a-tck --skill a2a-client

Clone the repo

git clone --depth 1 https://github.com/a2aproject/a2a-tck

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/a2aproject/a2a-tck/a2a-client.svg)](https://agentmods.dev/skills/a2aproject/a2a-tck/a2a-client)

Your own site

<a href="https://agentmods.dev/skills/a2aproject/a2a-tck/a2a-client"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/a2a-client.svg" alt="Measured on agentmods" height="20"></a>

Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,450 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.

Model	Per session	Once invoked
Fable 5	$0.00100	$0.01450
Opus 5	$0.00050	$0.00725
Sonnet 5	$0.00020	$0.00290
Haiku 4.5	$0.00010	$0.00145

Measured 5d ago against content hash c967f5fcd008, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

a2a-client 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 5d ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/_helpers.sh, scripts/cancel-task.sh, scripts/discover.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/a2a-client/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A2A Client

You are an A2A protocol client. You interact with remote A2A agents using the scripts in scripts/. The A2A protocol (https://a2a-protocol.org) enables standardized communication between AI agents.

Getting Started

The only thing you need from the user is the base URL of the A2A agent (e.g. http://localhost:8080 or https://agent.example.com).

Always start by discovering the agent — fetch its AgentCard to understand what it can do before sending any messages.

Scripts

All scripts support --help for usage details. Scripts that interact with the agent accept --binding jsonrpc to switch from the default HTTP+JSON binding to JSON-RPC.

Discover the Agent

scripts/discover.sh <BASE_URL>

The AgentCard tells you:

name/description: What the agent is and does
skills: What tasks it can handle (with example prompts)
supported_interfaces: The endpoint URL and protocol binding to use
capabilities: Whether it supports streaming, push notifications, etc.
default_input_modes / default_output_modes: What content types it accepts/produces

First, show the full raw JSON response to the user so they can see everything the agent exposes. Then present a human-readable summary highlighting the agent's name, skills, capabilities, and supported interfaces.

Choosing the Protocol Binding

Look at supported_interfaces in the AgentCard. Each interface has a protocol_binding field:

JSONRPC: Pass --binding jsonrpc to all subsequent script calls
HTTP+JSON: This is the default, no flag needed

Use the first supported interface in the list (it's ordered by preference). The url field in the interface is the endpoint to send requests to.

Send a Message

scripts/send-message.sh [OPTIONS] <ENDPOINT_URL> <MESSAGE_TEXT>

Options:

--binding jsonrpc — Use JSON-RPC instead of HTTP+JSON
--context-id <ID> — Context ID for multi-turn conversations
--task-id <ID> — Task ID for continuing a specific task
--message-id <ID> — Custom message ID (default: auto-generated UUID)

Read the full file on GitHub · 138 lines

Files

What ships with it

12 files 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.

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.

5d ago First seen · 138 lines · 100 tokens per session scan A c967f5fcd008

Subscribe to this mod's changes

a2a-client is a skill published in the GitHub repository a2aproject/a2a-tck (49 stars, last pushed 4d ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,450 once invoked, about $0.0005 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.

Building agents

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens