Borrowing it
Nothing to install: this file belongs to disler/learning-cmux-with-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/disler/learning-cmux-with-agents/main/.claude/skills/cmux/SKILL.mdgit clone --depth 1 https://github.com/disler/learning-cmux-with-agentsWrote 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.
[](https://agentmods.dev/skills/disler/learning-cmux-with-agents/cmux)<a href="https://agentmods.dev/skills/disler/learning-cmux-with-agents/cmux"><img src="https://agentmods.dev/badge/skills/disler/learning-cmux-with-agents/cmux/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.
<a href="https://agentmods.dev/skills/disler/learning-cmux-with-agents/cmux"><img src="https://agentmods.dev/badge/skills/disler/learning-cmux-with-agents/cmux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00065 | $0.02730 |
| Opus 5 | $0.00032 | $0.01365 |
| Sonnet 5 | $0.00013 | $0.00546 |
| Haiku 4.5 | $0.00006 | $0.00273 |
Grade B, and why
cmux scanned grade B with 1 finding 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 10d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
Bash/edits and instead print instructions, then end its turn. For a hands-off fleet How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux
Purpose
You are driving cmux, a CLI + socket for controlling terminal surfaces (and the agents running inside them). Every window, workspace, pane, and surface is a real, addressable object you can spawn, prompt, read, and close from the command line.
Instructions
Discover commands first (--help)
Before doing anything, run:
cmux --help
Then drill into any subcommand you intend to use:
cmux <command> --help # e.g. cmux workspace --help, cmux send --help
cmux evolves; trust --help over memory. Never guess flags — confirm them.
Understand the hierarchy
Everything nests in one tree. Learn the boxes and the verbs fall out:
- Window → a top-level OS window.
- Workspace → a sidebar entry ("tab") inside a window.
- Pane → a split region within a workspace.
- Surface → a tab within a pane (a terminal or a browser).
Use cmux tree --all (or cmux workspace list / cmux list-pane-surfaces) to see
the current state before you act.
Create a workspace and inject credentials (--env-file)
Create a workspace and capture BOTH refs in one call. --json returns the
workspace_ref and the initial surface_ref — grab and thread them; never guess
positional refs.
cmux workspace create --name <name> --cwd <dir> --env-file .env --json
cmux workspace createsupports--env-file, which loads that file's environment variables into every surface in the workspace — so an agent launched in a pane (claude,pi,codex,gemini) comes up already authenticated, no manualexportneeded.- Default
--env-fileto.env(the repo's.env) unless told otherwise:--env-file .env. That is the canonical source forOPENROUTER_API_KEY,ANTHROPIC_API_KEY, etc. - Pair it with
--layout <compact-json>to boot a whole multi-pane team declaratively in one call (each pane'scommandauto-launches its agent). - Don't inject over a working login. If an agent is already authenticated
(e.g. Claude Code), don't push a placeholder key over it via
--env-file; scope credential injection to the agents that actually need it. - Assume the keys are already set up — and never read their values. By
default, just point
--env-fileat.envand proceed; do notcat .env,echo $OPENROUTER_API_KEY, orread-screena surface to capture a key. Only if an agent actually fails to authenticate should you validate, and do it safely:cmux workspace env --workspace <ref> --maskshows that a var is present without revealing it, and[ -n "$VAR" ]confirms it is non-empty. Report the masked/presence result, never the secret itself.
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.
- 10d ago First seen · 213 lines · 65 tokens per session scan B 0d71f5002fec
cmux is a skill published in the GitHub repository disler/learning-cmux-with-agents (109 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 2,730 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…