a2a-client

a2a-client is a skill for Claude Code, Codex from OpenLinkSoftware/ai-agent-skills. It costs 121 tokens per session (1,246 once invoked), scanned A, original, MIT.

A client for connecting to OPAL Agent2Agent services, which are remote AI-agent endpoints that accept tasks. It can discover an agent's description, authenticate, send tasks, follow streamed updates, and retrieve results.

In plain words
What is it for?
Use it to call OPAL agents, continue an existing task session, upload files, or test an Agent2Agent endpoint.
Why use it?
It removes the need to implement the protocol, login flow, task requests, and streamed status handling yourself.

Skill for Claude CodeCodex

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/openlinksoftware/ai-agent-skills/a2a-client
Any agent
npx skills add OpenLinkSoftware/ai-agent-skills --skill a2a-client
Clone the repo
git clone --depth 1 https://github.com/OpenLinkSoftware/ai-agent-skills

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-client

README.md
[![agentmods](https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/a2a-client.svg)](https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/a2a-client)
Your own site
<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/a2a-client"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/a2a-client.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,246 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 $0.00121 $0.01246
Opus 5 $0.00060 $0.00623
Sonnet 5 $0.00024 $0.00249
Haiku 4.5 $0.00012 $0.00125

Measured 5d ago against content hash 1b936112bc9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 1 executable file (scripts/a2a_client.py), 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.

a2a-client/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OPAL A2A Client

Use this skill to interact with an OPAL backend that implements the Agent2Agent protocol.

Required Elicitations

Before making any request, obtain these runtime values from the user, environment, or an already verified project config:

  • Target endpoint: either an HTTPS base URL such as https://{CNAME} or a full A2A URL such as https://{CNAME}/chat/api/a2a; CLI args win over OPAL_A2A_BASE_URL, OPAL_A2A_CNAME, OPAL_A2A_URL, and OPAL_A2A_CARD_URL.
  • Authentication mode: bearer/API key, dynamic OAuth Authorization Code, OAuth2 client credentials, or no request until credentials are supplied.
  • Credential source: environment variable name, secret manager reference, dynamic OAuth flow, or user-provided value. The script recognizes OPAL_A2A_TOKEN_ENV and OPAL_A2A_TOKEN; do not echo secrets.
  • Interaction mode: tasks/send, tasks/sendSubscribe, or tasks/get.
  • Session behavior: new context/session or continue with a supplied contextId or sessionId.

Do not silently substitute a default CNAME. Present the recommended endpoints below as choices, accept a custom endpoint, or use a verified override such as OPAL_A2A_BASE_URL or OPAL_A2A_CNAME.

Offer these as non-exclusive choices when the user has not supplied a target:

  1. https://netid-qa.openlinksw.com:8443
  2. https://linkeddata.uriburner.com
  3. https://demo.openlinksw.com

Also offer a custom base URL or full /chat/api/a2a endpoint. Do not assume the first endpoint is the default; wait for the user's selection or a verified config/env override.

Workflow

  1. Normalize the target:
    • If the user gives a base URL, fetch the Agent Card from /.well-known/agent.json and derive the A2A endpoint from the card's url field.
    • If the user gives a full /chat/api/a2a URL, derive the Agent Card URL from the same origin unless the user supplies a separate card URL.
  2. Fetch and inspect the Agent Card before sending tasks. Confirm name, provider, auth schemes, capabilities, input modes, output modes, and listed skills.
  3. Authenticate:
    • For bearer/API key, send Authorization: Bearer {token}.
    • Prefer bearer tokens via --token-env, OPAL_A2A_TOKEN_ENV, or OPAL_A2A_TOKEN rather than raw --token.
    • For interactive OAuth, use dynamic client registration plus Authorization Code flow with --oauth-auth-code; register against the selected endpoint's own issuer, not a different host.
    • To reuse an OAuth-acquired bearer token, use --save-token-env OPAL_A2A_TOKEN --save-token-env-file .opal-a2a.env, then source the file in a shell you control.
    • For OAuth2 client credentials, use the card's token URL when present, or elicit an explicit token URL.
    • Never log tokens, client secrets, or complete Authorization headers.
  4. Choose the task method:
    • Use tasks/send for a single request/response task.
    • Use tasks/sendSubscribe when the user asks for streaming or the card advertises streaming support and the user chooses it.
    • Use tasks/get to check an existing task ID.
  5. Build JSON-RPC 2.0 payloads with text parts by default. Include attachments only from user-approved file paths.
  6. Preserve returned task id, contextId, and sessionId values. Ask whether to continue the same context when the next request depends on prior task state.
  7. Summarize results from status.message.parts, artifacts.parts, and final task state. Include IDs needed for follow-up, but keep secrets redacted.

Read the full file on GitHub · 76 lines

Files

What ships with it

3 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.

  1. 5d ago First seen · 76 lines · 121 tokens per session scan A 1b936112bc9b

Subscribe to this mod's changes

a2a-client is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 1,246 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens