A router for sending plain-language requests to coding agents such as Pi, Claude Code, Codex, OpenCode, Gemini CLI, or other ACP harnesses. ACP is a way for tools to communicate with coding-agent sessions.

Use it to start or continue work in an external coding agent, relay instructions, or keep a thread-like conversation with that agent. Coding-agent thread requests follow its required session-spawning path.

It removes the need to decide how each coding agent should be started or continued. It chooses between the available session-based route and direct acpx driving according to the request and system health.

acp-router — Skill for Claude Code and Codex by YeSongYun

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 YeSongYun/openclaw-cn --skill acp-router

Clone the repo

git clone --depth 1 https://github.com/YeSongYun/openclaw-cn

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/yesongyun/openclaw-cn/acp-router/github.svg)](https://agentmods.dev/skills/yesongyun/openclaw-cn/acp-router)

Your own site

<a href="https://agentmods.dev/skills/yesongyun/openclaw-cn/acp-router"><img src="https://agentmods.dev/badge/skills/yesongyun/openclaw-cn/acp-router/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yesongyun/openclaw-cn/acp-router"><img src="https://agentmods.dev/badge/skills/yesongyun/openclaw-cn/acp-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,951 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 100% copy Near-identical to another mod 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 5.1	$0.00069	$0.01951
Opus 5	$0.00034	$0.00975
Sonnet 5	$0.00014	$0.00390
Haiku 4.5	$0.00007	$0.00195

Measured 12d ago against content hash 80f5a6382fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

acp-router 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.

Origin

This is a copy

100% identical to acp-router — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

extensions/acpx/skills/acp-router/SKILL.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ACP Harness Router

When user intent is "run this in Pi/Claude Code/Codex/OpenCode/Gemini/Kimi (ACP harness)", do not use subagent runtime or PTY scraping. Route through ACP-aware flows.

Intent detection

Trigger this skill when the user asks OpenClaw to:

run something in Pi / Claude Code / Codex / OpenCode / Gemini
continue existing harness work
relay instructions to an external coding harness
keep an external harness conversation in a thread-like conversation

Mandatory preflight for coding-agent thread requests:

Before creating any thread for Pi/Claude/Codex/OpenCode/Gemini work, read this skill first in the same turn.
After reading, follow OpenClaw ACP runtime path below; do not use message(action="thread-create") for ACP harness thread spawn.

Mode selection

Choose one of these paths:

OpenClaw ACP runtime path (default): use sessions_spawn / ACP runtime tools.
Direct acpx path (telephone game): use acpx CLI through exec to drive the harness session directly.

Use direct acpx when one of these is true:

user explicitly asks for direct acpx driving
ACP runtime/plugin path is unavailable or unhealthy
the task is "just relay prompts to harness" and no OpenClaw ACP lifecycle features are needed

Do not use:

subagents runtime for harness control
/acp command delegation as a requirement for the user
PTY scraping of pi/claude/codex/opencode/gemini/kimi CLIs when acpx is available

AgentId mapping

Use these defaults when user names a harness directly:

"pi" -> agentId: "pi"
"claude" or "claude code" -> agentId: "claude"
"codex" -> agentId: "codex"
"opencode" -> agentId: "opencode"
"gemini" or "gemini cli" -> agentId: "gemini"
"kimi" or "kimi cli" -> agentId: "kimi"

These defaults match current acpx built-in aliases.

If policy rejects the chosen id, report the policy error clearly and ask for the allowed ACP agent id.

OpenClaw ACP runtime path

Required behavior:

For ACP harness thread spawn requests, read this skill first in the same turn before calling tools.
Use sessions_spawn with:
- runtime: "acp"
- thread: true
- mode: "session" (unless user explicitly wants one-shot)
For ACP harness thread creation, do not use message with action=thread-create; sessions_spawn is the only thread-create path.
Put requested work in task so the ACP session gets it immediately.
Set agentId explicitly unless ACP default agent is known.
Do not ask user to run slash commands or CLI when this path works directly.

Read the full file on GitHub · 220 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.

12d ago First seen · 220 lines · 69 tokens per session scan A 80f5a6382fa6

Subscribe to this mod's changes

acp-router is a skill published in the GitHub repository YeSongYun/openclaw-cn (56 stars, last pushed 3mo ago), licensed MIT. It adds 69 tokens to every session and 1,951 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to acp-router, differing in 0 lines, and is treated as a copy.

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

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

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