Mux

An agent configuration for starting coder/mux through an ACP connection. Mux is a coding-agent service, and ACP is the bridge used to communicate with it.

In plain words
What is it for?
Use it to launch mux through `mux acp`, configure provider credentials, or connect to a remote mux server with its URL and authentication token.
Why use it?
It lets an agent start mux automatically and connect it to a configured model provider without requiring a separate mux server.

Agent

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/openclaw/acpx/mux
Clone the repo
git clone --depth 1 https://github.com/openclaw/acpx
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 201 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 $0.00000 $0.00201
Opus 5 $0.00000 $0.00101
Sonnet 5 $0.00000 $0.00040
Haiku 4.5 $0.00000 $0.00020

Measured 2d ago against content hash c759cdb10d37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Mux 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 2d 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/Mux.md · 10 lines

What it actually says

Mux

acpx mux starts coder/mux through its ACP stdio bridge (mux acp). mux acp auto-starts an in-process mux server, so a separate mux server is not required.

Configure at least one model provider before prompting (for example ANTHROPIC_API_KEY, OPENAI_API_KEY, or OPENROUTER_API_KEY); see https://mux.coder.com/config/providers. When using direct provider keys, make sure mux route priority includes direct before providers you have not authenticated. To target a remote mux server, override the command with mux acp --server-url <url> --auth-token <token> (or set MUX_SERVER_URL / MUX_SERVER_AUTH_TOKEN).

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. 2d ago First seen · 10 lines · 0 tokens per session scan A c759cdb10d37

Subscribe to this mod's changes

Mux is an agent published in the GitHub repository openclaw/acpx (3,202 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 201 tokens. 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.

Related

Other agents, from other repositories