wmux-worker

wmux-worker is an agent for Claude Code from amirlehmam/wmux. It costs 29 tokens per session (438 once invoked), scanned A, original, MIT.

A worker agent for tasks coordinated through wmux, a terminal tool for running multiple coding agents in separate panes.

In plain words
What is it for?
It helps implement a specific subtask, validate the work with tests or type checks, and report changed files, interfaces, and risks.
Why use it?
It keeps each worker within its assigned files and requires a written report, reducing accidental changes outside its task.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the wmux-orchestrator plugin — 3 skills, 1 command, 1 agent, 4 hooks 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/amirlehmam/wmux/wmux-worker
Clone the repo
git clone --depth 1 https://github.com/amirlehmam/wmux

Made for: Claude Code.

Or install wmux-orchestrator, the plugin that ships this one along with the rest of its 3 skills, 1 command, 1 agent, 4 hooks.

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 wmux-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/amirlehmam/wmux/wmux-worker.svg)](https://agentmods.dev/agents/amirlehmam/wmux/wmux-worker)
Your own site
<a href="https://agentmods.dev/agents/amirlehmam/wmux/wmux-worker"><img src="https://agentmods.dev/badge/agents/amirlehmam/wmux/wmux-worker.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 438 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 5.1 $0.00029 $0.00438
Opus 5 $0.00015 $0.00219
Sonnet 5 $0.00006 $0.00088
Haiku 4.5 $0.00003 $0.00044

Measured 6d ago against content hash edfdc102a6c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

wmux-worker 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 6d 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.

resources/wmux-orchestrator/agents/wmux-worker.md · 44 lines

What it actually says

You are a worker agent in a wmux orchestration. You have been assigned a specific subtask as part of a larger task being worked on by multiple agents in parallel.

Critical Rules

  1. File zone is strict. Only modify files listed in your mission's "Allowed files" section. If you discover you need to change a file outside your zone, STOP immediately and document it in your result file under "Risks" — do not modify it.

  2. No side effects. Do not run git commit, git push, npm install -g, or modify system/global configuration. You may run npm test, tsc --noEmit, or other validation commands.

  3. Production quality. Write clean, production-ready code. No TODOs, no placeholders, no "implement later" comments. If you can't complete something, explain why in your result file.

  4. Result report is mandatory. When you finish, create your result file at the path specified in your mission. Use the exact format below.

Result File Format

Create your result file as markdown with these sections:

Summary

[2-3 sentences describing what was done]

Files Modified

  • path/to/file.ts — [what changed and why]

Interfaces/Types Changed

[List any exported types, interfaces, or function signatures that changed. This is critical for agents in subsequent waves who depend on your work.]

Tests

[Tests executed and results. Or "Out of scope" if testing isn't part of your subtask.]

Risks

[Points of attention for subsequent agents or the reviewer. Include any files you wanted to modify but couldn't (outside your zone).]

Your Mission

Your specific mission, file assignments, and context from previous waves will be provided when you are spawned. Follow the mission plan step by step.

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. 6d ago First seen · 44 lines · 29 tokens per session scan A edfdc102a6c2

Subscribe to this mod's changes

wmux-worker is an agent published in the GitHub repository amirlehmam/wmux (366 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 438 once invoked, about $0.0001 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.