New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

A2a Protocol

by agntcy in agntcy/coffeeAgntcy

A skill your agent uses when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage.

Apache-2.0Auto-check passedAgent Workflows

Install A2a Protocol

skills CLI
$ npx skills add agntcy/coffeeAgntcy --skill a2a-protocol -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agntcy/coffeeAgntcy a2a-protocol --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agntcy/coffeeAgntcy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/coffeeAGNTCY/coffee_agents/recruiter/coding-agent-integrations/claude-code/plugin/skills/a2a-protocol .claude/skills/a2a-protocol && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
a2a-protocol
GitHub stars
112
Token cost
~1k tokens
SKILL.md length
482 words
Files
5 (incl. references)
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage.

  • Works in 3 steps: /recruit - discover agents, pick which… → Invoke with: / - e.g.,… → Delete by removing the directory: rm -rf…
  • The user asks about A2A (Agent-to-Agent) protocol communication
  • SKILL.md covers Recruited Agents, Core Concepts, Protocol and Reference Files
  • Calls curl

What it does

A2a Protocol is an agent skill from agntcy/coffeeAgntcy. Use this skill when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage. It provides comprehensive reference material for A2A integrations.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/a2a-protocol-cheatsheet.md`, `references/dirctl-search.md` and `references/error-handling.md`).

It sits in Agent Workflows, covering Subagents. It works with Agent2Agent Protocol. The repository describes itself as: End-to-end reference application for AGNTCY Components. The licence is Apache-2.0.

When your agent uses it

  • The user asks about A2A (Agent-to-Agent) protocol communication
  • OASF record formats
  • AGNTCY directory operations
  • Agent card parsing

Example prompts

  • “/a2a-protocol”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. /recruit - discover agents, pick which to create, choose "skill" mode
  2. Invoke with: / - e.g., /brazil-coffee-farm What is the current yield?
  3. Delete by removing the directory: rm -rf .claude/skills//

What it can do on your machine

Read from SKILL.md and the folder at commit 36f1923. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

A2a Protocol loads about 1k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 482 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from agntcy/coffeeAgntcy at commit 36f1923, republished under its Apache-2.0 licence (© agntcy). 482 words, ~1,024 tokens.

Download SKILL.mdSave it as .claude/skills/a2a-protocol/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
a2a-protocol
description
Use this skill when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage. It provides comprehensive reference material for A2A integrations.

A2A Protocol Skill

This skill provides knowledge about the A2A (Agent-to-Agent) protocol, the AGNTCY directory, and the OASF (Open Agent Standard Format) - everything needed to discover, connect to, and communicate with remote agents.

Recruited Agents

The /recruit command discovers agents from the AGNTCY directory and connects them to Claude Code. Two creation modes are available:

Skills create a /slash-command that the parent model executes directly. This is the most reliable way to proxy requests because the parent model runs the a2a-send command itself - no intermediary model to refuse.

Workflow:

  1. /recruit <query> - discover agents, pick which to create, choose "skill" mode
  2. Invoke with: /<agent-name> <message> - e.g., /brazil-coffee-farm What is the current yield?
  3. Delete by removing the directory: rm -rf .claude/skills/<agent-name>/

Skills are available immediately after creation - no restart needed.

Sub-Agents

Sub-agents create a .claude/agents/<name>.md file. Claude Code spawns a separate model to handle requests. This is useful when you want the sub-agent to have its own model (haiku/sonnet/opus) and reasoning, but note that sub-agent models may refuse to forward requests they deem outside the agent's advertised capabilities.

Workflow:

  1. /recruit <query> - discover agents, pick which to create, choose "subagent" mode
  2. Use them: "use the coffee-farm agent to check the yield" → Claude Code dispatches the sub-agent automatically
  3. Delete by removing the file: rm .claude/agents/coffee-farm.md

Sub-agents require a restart to load - run /exit and relaunch claude.

Core Concepts

A2A Protocol

A2A (Agent-to-Agent) is a JSON-RPC 2.0 protocol for inter-agent communication over HTTP. This plugin uses v0.3.0+ (message/send method). Always check the protocolVersion in an agent's card to confirm compatibility.

OASF (Open Agent Standard Format)

OASF records are the standard format for describing agents in the AGNTCY directory. Each record contains metadata (name, description, skills, domains) and modules - including the integration/a2a module that holds the Agent Card.

Show full SKILL.md (182 more words)Show less
AGNTCY Directory

A directory where agents register their OASF records. The dirctl CLI is the primary interface:

  • dirctl search - find agents by skill, name, domain, or module → returns CIDs
  • dirctl pull <CID> - fetch the full OASF record for a CID

The directory server address is configured via DIRECTORY_CLIENT_SERVER_ADDRESS (default 0.0.0.0:8888).

Agent Card

The A2A Agent Card (found inside the integration/a2a module of an OASF record) describes an agent's communication interface: endpoint URL, supported protocol version, skills, capabilities, and transport options. It can also be fetched directly at <endpoint>/.well-known/agent.json.

Protocol

A2A uses JSON-RPC 2.0 over HTTP POST with the message/send method (v0.3.0+). Key format details:

  • Messages require a messageId field (UUID)
  • Parts use "kind": "text"
  • Multi-turn uses contextId in configuration
  • Response: result.kind: "message" with result.parts[]
Version Detection
bash
curl -s <ENDPOINT_URL>/.well-known/agent.json

Check protocolVersion - must be "0.3.0" or higher.

Reference Files

For detailed information, see these reference files in the references/ directory:

FileContents
oasf-structure.mdOASF record fields, Agent Card fields, HTTP endpoint resolution
a2a-protocol-cheatsheet.mdProtocol version detection, method tables, curl templates, response formats
error-handling.mdTimeouts, retry policy, structured error format
dirctl-search.mddirctl search and pull command examples

© agntcy, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in coffeeAGNTCY/coffee_agents/recruiter/coding-agent-integrations/claude-code/plugin/skills/a2a-protocol of agntcy/coffeeAgntcy.

  • SKILL.md
  • references/a2a-protocol-cheatsheet.md
  • references/dirctl-search.md
  • references/error-handling.md
  • references/oasf-structure.md

Open the folder on GitHubat commit 36f1923

Compare with similar skills

A2a Protocol next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

A2a Protocol compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
A2a Protocol this skillagntcy/coffeeAgntcy112—~1kAutomated safety check: PassApache-2.0
Claude Code Agent Developmentanthropics/claude-plugins-official37k8 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25840 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    37k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 40 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from agntcy/coffeeAgntcy

All 16 skills in this repo

  • Add Repo Operation

    agntcy/coffeeAgntcy

    Guides adding a new repository operation (a check, validation, or piece of tooling) through this repo's standard script - Taskfile task - skill - CI enforcement - rule pipeline.

    112 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed

  • Agentic Workflows API Documentation Lungo

    agntcy/coffeeAgntcy

    Authors and maintains the human-facing Agentic Workflows API documentation for the lungo subproject at coffeeAGNTCY/coffeeagents/lungo/docs/workflow-instanceapi.md.

    112 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

  • Checking Pinned References

    agntcy/coffeeAgntcy

    Runs task pins:check to find any third-party GitHub Action, reusable-workflow, or image reference that isn't pinned to an immutable SHA/digest, and pins each one it finds.

    112 GitHub stars~578 tokensUpdated yesterday
    Auto-check passed

  • Checking Workflow Permissions

    agntcy/coffeeAgntcy

    Runs task workflows:check-permissions to find any GitHub Actions workflow file with a write-all grant or no declared permissions, and scopes it down to least privilege.

    112 GitHub stars~513 tokensUpdated yesterday
    Auto-check passed

  • Generate Release Notes

    agntcy/coffeeAgntcy

    Generates coffeeAgntcy CHANGELOG release notes and README Built With updates from PRs and dependency lockfiles since the previous release tag.

    112 GitHub stars~535 tokensUpdated yesterday
    Auto-check passed

  • Linting GitHub Workflows

    agntcy/coffeeAgntcy

    Runs task workflows:lint (actionlint) against every file under .github/workflows/ and fixes what it reports.

    112 GitHub stars~507 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about A2a Protocol

What does A2a Protocol do?

A skill your agent uses when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage. A2a Protocol is an agent skill from agntcy/coffeeAgntcy. Use this skill when the user asks about A2A (Agent-to-Agent) protocol communication, OASF record formats, AGNTCY directory operations, agent card parsing, or dirctl CLI usage.

When should I use A2a Protocol?

A2a Protocol fits situations like: the user asks about A2A (Agent-to-Agent) protocol communication; OASF record formats; AGNTCY directory operations; agent card parsing.

How do I install A2a Protocol in Claude Code?

Run `npx skills add agntcy/coffeeAgntcy --skill a2a-protocol -a claude-code`. Or copy the skill folder (coffeeAGNTCY/coffee_agents/recruiter/coding-agent-integrations/claude-code/plugin/skills/a2a-protocol in agntcy/coffeeAgntcy) into .claude/skills/a2a-protocol in your project. Claude Code loads it when a task matches its description.

How do I install A2a Protocol in Codex?

Run `npx skills add agntcy/coffeeAgntcy --skill a2a-protocol -a codex`. Or copy the skill folder (coffeeAGNTCY/coffee_agents/recruiter/coding-agent-integrations/claude-code/plugin/skills/a2a-protocol in agntcy/coffeeAgntcy) into .agents/skills/a2a-protocol in your project. Codex loads it when a task matches its description.

Can I use A2a Protocol in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agntcy/coffeeAgntcy --skill a2a-protocol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/a2a-protocol, .gemini/skills/a2a-protocol, .github/skills/a2a-protocol and .opencode/skills/a2a-protocol in your project.

What does A2a Protocol need to run?

Going by SKILL.md and its folder, A2a Protocol needs the command-line tools its instructions call (curl).

Does A2a Protocol access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is A2a Protocol safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does A2a Protocol use?

A2a Protocol is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does A2a Protocol use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.

What are the alternatives to A2a Protocol?

Skills that share tags, products or a category with A2a Protocol: Claude Code Agent Development (anthropics/claude-plugins-official, 37k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains A2a Protocol?

agntcy (a GitHub organization) maintains it in agntcy/coffeeAgntcy, which has 112 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on October 6, 2026.

Source: agntcy/coffeeAgntcy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.