ag2-acp

ag2-acp is a skill for Claude Code, Codex from ag2ai/ag2-skills. It costs 161 tokens per session (2,828 once invoked), scanned A, original, Apache-2.0.

A way for AG2, a Python framework for building AI agents, to run command-line coding agents such as Claude Code, Codex, or OpenCode through the Agent Client Protocol. Their messages, plans, tool calls, and permission requests become observable AG2 events.

In plain words
What is it for?
Use it to orchestrate coding agents in automated refactoring or batch workflows, observe their work, require approval for sensitive actions, and confine file access to a chosen workspace.
Why use it?
It lets a program monitor and control external coding agents instead of treating them as opaque processes. File writes and terminal commands can be restricted to a workspace or approved by a person.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

Good fit Use it to orchestrate coding agents in automated refactoring or batch workflows, observe their work, require approval for sensitive actions, and confine file access to a chosen workspace.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ag2ai/ag2-skills/ag2-acp
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.

Any agent
npx skills add ag2ai/ag2-skills --skill ag2-acp
Clone the repo
git clone --depth 1 https://github.com/ag2ai/ag2-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 ag2-acp

README.md
[![agentmods](https://agentmods.dev/badge/skills/ag2ai/ag2-skills/ag2-acp/github.svg)](https://agentmods.dev/skills/ag2ai/ag2-skills/ag2-acp)
Your own site
<a href="https://agentmods.dev/skills/ag2ai/ag2-skills/ag2-acp"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-skills/ag2-acp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ag2-acp

Your own site · 80×15
<a href="https://agentmods.dev/skills/ag2ai/ag2-skills/ag2-acp"><img src="https://agentmods.dev/badge/skills/ag2ai/ag2-skills/ag2-acp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,828 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00161 $0.02828
Opus 5 $0.00081 $0.01414
Sonnet 5 $0.00032 $0.00566
Haiku 4.5 $0.00016 $0.00283

Measured 12d ago against content hash ecb98b3db584, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ag2-acp 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 12d 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.

skills/ag2-acp/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI coding agents over ACP

Drive external CLI coding agents — Claude Code, Codex, OpenCode — as first-class AG2 Agents, using the Agent Client Protocol (ACP). AG2 plays the ACP Client role; each CLI agent runs as an ACP Agent subprocess. Everything the agent does — message output, thinking, tool calls, plans, permission prompts — is externalized onto AG2's event stream, so you can observe, gate, and orchestrate it like any other AG2 agent.

The integration is just a config class (ACPConfig and its presets) — no changes to the Agent API.

When to use

  • You want to orchestrate CLI coding agents from Python: headless refactoring pipelines, "manager" agents delegating to coder agents, batch code-mod runs.
  • You want to observe a coding agent's work live — thoughts, tool calls, plans — on the AG2 event stream.
  • You want to gate the agent's sensitive actions (file writes, shell commands) with a permission policy or a human in the loop.
  • You need the agent's file access confined to a workspace root (fs_root) and its terminal use mediated by AG2.

Not this skill: exposing an AG2 agent to other systems — that is ag2-a2a (A2A protocol) or ag2-mcp (MCP server). For the HITL input plumbing that permission_policy="ask" relies on, see ag2-hitl.

Installation

pip install "ag2[acp]"

The acp extra pulls in the agent-client-protocol SDK. Each CLI agent additionally needs its own ACP adapter on PATH:

Agent Adapter install Auth
Claude Code npm i -g @agentclientprotocol/claude-agent-acp (bin claude-agent-acp) ANTHROPIC_API_KEY in env, or CLAUDE_CONFIG_DIR pointing at an existing Claude Code login
Codex npm i -g @agentclientprotocol/codex-acp (bin codex-acp) CODEX_API_KEY (takes precedence) or OPENAI_API_KEY
OpenCode opencode CLI itself (opencode acp) opencode auth login (or env / .env)

No global install? Override the launch command to use npx: ClaudeCodeConfig(command=["npx", "-y", "@agentclientprotocol/claude-agent-acp"]).

Read the full file on GitHub · 209 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. 12d ago First seen · 209 lines · 161 tokens per session scan A ecb98b3db584

Subscribe to this mod's changes

ag2-acp is a skill published in the GitHub repository ag2ai/ag2-skills (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 161 tokens to every session and 2,828 once invoked, about $0.0008 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 2026-08-31.

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

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