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.
npx agentmods add instructions/openclaw/acpx/agents-mdgit clone --depth 1 https://github.com/openclaw/acpxWhat 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 | $0.03976 | $0.03976 |
| Opus 5 | $0.01988 | $0.01988 |
| Sonnet 5 | $0.00795 | $0.00795 |
| Haiku 4.5 | $0.00398 | $0.00398 |
Grade A, and why
acpx AGENTS.md 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — acpx
Purpose
This file is for contributors and coding agents working in this repository.
Keep it focused on how to develop, validate, and ship acpx.
Use these files for the other concerns:
README.mdfor user-facing install and usagedocs/CLI.mdfor CLI referenceVISION.mdfor product direction and boundariesCONTRIBUTING.mdfor PR expectationsskills/acpx/SKILL.mdfor agent-usage guidance
When you need implementation detail, prefer the in-repo references below instead of expanding this file into a full technical spec.
Repo
- GitHub:
https://github.com/openclaw/acpx - npm:
https://www.npmjs.com/package/acpx - Default branch:
main - Runtime: Node.js
>=22.13.0 - Package manager:
[email protected] - Clean Node 22.13 setups can have stale Corepack signing keys; install pnpm
with
npm install -g [email protected]ifcorepack preparefails.
Product Direction
acpxshould be the smallest useful ACP client: a lightweight CLI that lets one agent talk to another agent through the Agent Client Protocol without PTY scraping or adapter-specific glue.- The goal is not to build a giant orchestration layer. The goal is to make ACP practical, robust, and easy to compose in real workflows.
- The primary user is another agent, orchestrator, or harness. Human usability still matters, but it is a secondary constraint.
acpxshould not try to do too many things at once.- If a feature does not make
acpxa better ACP client or backend, it probably does not belong in core. - In
acpx, data models, config keys, keywords, flags, output shapes, and naming conventions are part of the product surface. - They should be scrutinized multiple times before being added or changed. Convenience is not enough. Every new convention creates long-term compatibility cost.
- The default stance should be to add fewer conventions, make them clearer, and keep them stable.
- Read
VISION.mdbefore changing user-visible behavior or conventions.
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.
- yesterday First seen · 333 lines · 3,976 tokens per session scan A 2f093ea6ca31
acpx AGENTS.md is an instructions file published in the GitHub repository openclaw/acpx (3,194 stars, last pushed 3d ago), licensed MIT. It adds 3,976 tokens to every session, about $0.0199 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.
Other instructions, from other repositories
harnss CLAUDE.md
Instructions for OpenSource03/harnss, covering harnss, tech stack, project structure, how to run and architecture.
harnss AGENTS.md
Instructions for OpenSource03/harnss, a project described as: Open-source, desktop client/UI build to harness Claude Code, Codex and any other Agent accepting Agent Client Protocol. Run multiple AI coding agents side by side with rich tool visualization, MCP integrations, built-in terminal, git, browser and just about…
acp-server CLAUDE.md
Claude Code instructions for kinshuksarabhai/acp-server, covering claude.md, project overview, development commands, running the server and or directly.
acp-server AGENTS.md
AGENTS.md instructions for kinshuksarabhai/acp-server, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).