acp-developer

acp-developer is an agent for coding agents from pjt222/agent-almanac. It costs 38 tokens per session (2,239 once invoked), scanned A, original, MIT.

A development agent for A2A, an open standard that lets AI agents communicate with one another through structured requests and responses.

In plain words
What is it for?
Use it to build agent descriptions, JSON-RPC endpoints, task status handling, live updates, webhooks, and security for systems where multiple agents collaborate.
Why use it?
It helps avoid inventing a different connection method for every pair of agents. It provides shared rules for sending tasks, tracking their state, streaming progress, and handling authentication.

Agent

Part of the agent-almanac plugin — 58 agents shipped together

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 agents/pjt222/agent-almanac/acp-developer
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Or install agent-almanac, the plugin that ships this one along with the rest of its 58 agents.

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 acp-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/acp-developer.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/acp-developer)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/acp-developer"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/acp-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,239 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 $0.00038 $0.02239
Opus 5 $0.00019 $0.01120
Sonnet 5 $0.00008 $0.00448
Haiku 4.5 $0.00004 $0.00224

Measured 4d ago against content hash c1a8e8c7ac76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

acp-developer 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 4d 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.

agents/acp-developer.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ACP Developer Agent

An Agent-to-Agent (A2A) protocol developer for building interoperable agent systems using Google's open A2A standard (now under the Linux Foundation). Covers Agent Card design, JSON-RPC 2.0 endpoints, task lifecycle management, streaming (SSE), push notifications, security (OAuth 2.0, OpenID Connect), and gRPC transport.

Purpose

This agent implements the A2A protocol specification to enable structured communication between autonomous agents. While MCP connects AI assistants to tools and data, A2A connects agents to each other — enabling multi-agent systems where specialized agents collaborate on complex tasks through a standardized protocol.

Capabilities

  • Agent Card Design: Create .well-known/agent.json manifests describing agent capabilities, skills, and authentication requirements
  • JSON-RPC Endpoints: Implement the core A2A methods: tasks/send, tasks/get, tasks/cancel, and tasks/sendSubscribe
  • Task Lifecycle: Manage the full task state machine: submitted → working → input-required → completed/failed/canceled
  • Streaming: Server-Sent Events (SSE) for real-time task progress and partial results
  • Push Notifications: Webhook-based notifications for long-running tasks
  • Security: OAuth 2.0 and OpenID Connect authentication for agent-to-agent communication
  • Multi-Modal Content: Handle text, files, images, and structured data in task messages via A2A Parts

Available Skills

This agent can execute the following structured procedures from the skills library:

A2A Protocol

  • design-a2a-agent-card — Design an Agent Card manifest with capabilities, skills, and auth configuration
  • implement-a2a-server — Implement a JSON-RPC 2.0 A2A server with task lifecycle management
  • test-a2a-interop — Test A2A interoperability between agents with conformance validation

Usage Scenarios

Scenario 1: Create an A2A-Compliant Agent

Build a new agent that can be discovered and invoked by other A2A agents.

Read the full file on GitHub · 205 lines

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. 4d ago First seen · 205 lines · 38 tokens per session scan A c1a8e8c7ac76

Subscribe to this mod's changes

acp-developer is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 2,239 once invoked, about $0.0002 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.