Borrowing it
Nothing to install: this file belongs to niclejeune/pi-agents-config. 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/niclejeune/pi-agents-config/main/.pi/agent/skills/cmux/SKILL.mdgit clone --depth 1 https://github.com/niclejeune/pi-agents-configWrote 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/niclejeune/pi-agents-config/cmux)<a href="https://agentmods.dev/skills/niclejeune/pi-agents-config/cmux"><img src="https://agentmods.dev/badge/skills/niclejeune/pi-agents-config/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/niclejeune/pi-agents-config/cmux"><img src="https://agentmods.dev/badge/skills/niclejeune/pi-agents-config/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 | $0.00050 | $0.03483 |
| Opus 5 | $0.00025 | $0.01741 |
| Sonnet 5 | $0.00010 | $0.00697 |
| Haiku 4.5 | $0.00005 | $0.00348 |
Grade A, and why
cmux 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 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.
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 — 437 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux Terminal & Browser Management
Use this skill when you need to run processes in separate terminals you can observe and control — dev servers, test watchers, build processes, or any long-running task. Also use it to open browser surfaces for testing web pages, taking screenshots, clicking elements, and reading page content.
Prerequisite: You must be running inside cmux (check for CMUX_SOCKET_PATH
in the environment). If it's not set, these commands won't work.
Default approach: Prefer creating surfaces (tabs) in the current
workspace over spawning new workspaces. Tabs keep everything grouped together
and are less disruptive. Only use new-workspace when you need full isolation
(e.g., a completely separate project).
Environment Variables
cmux auto-sets these in every shell it spawns:
| Variable | Purpose |
|---|---|
CMUX_WORKSPACE_ID |
UUID of the current workspace |
CMUX_SURFACE_ID |
UUID of the current surface/panel |
CMUX_SOCKET_PATH |
Unix socket path (usually /tmp/cmux.sock) |
Commands run inside a cmux shell automatically target the right workspace
without needing --workspace.
Core Commands
Create a new tab (surface) in the current workspace
cmux new-surface --type terminal
# Returns: OK surface:<n> pane:<n> workspace:<n>
This is the preferred way to spawn a new shell. It creates a tab next to the current terminal in the same workspace.
Create a new split pane
cmux new-split <left|right|up|down>
cmux new-pane --direction <left|right|up|down> [--type terminal]
Spawn a new workspace (for full isolation)
cmux new-workspace [--cwd <path>] [--command "<text>"]
# Returns: OK workspace:<n>
Send commands
cmux send --surface <ref> '<command>\n'
The \n sends Enter. Without it, text is typed but not executed.
Read terminal output
cmux read-screen --surface <ref> [--lines <n>] [--scrollback]
- Default: visible screen only
--scrollback: include scrollback buffer--lines <n>: limit to last N lines (implies scrollback)
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 · 437 lines · 50 tokens per session scan A 29dd3e726312
cmux is a skill published in the GitHub repository niclejeune/pi-agents-config (1 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 3,483 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
workspace-explorer
Explore and navigate Notion workspaces via MCP. Use when searching for pages, understanding database structure, finding content, creating or updating pages/databases, or managing Notion workspace content. Triggers when user asks about Notion, mentions Notion pages/databases, wants to find something in their wiki…
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack…
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
discovery-question-form
Structured clarification form for unresolved material requirements.
Interceptor
Real Chrome/Brave + macOS Computer Use from inside the browser — zero CDP fingerprint, real sessions; mandatory for visual deploy verification. Drive clickwork yourself. USE WHEN verify deploy, confirm UI, screenshot verification, computer use, macos automation, debug web, troubleshoot, visual check, motion/animation…
cli-anything-macrocli
Use when the agent wants to define, list, inspect, or execute GUI macros via the MacroCLI CLI. Macros are parameterized, CLI-callable workflows — the agent invokes macro run and the system handles backend routing (plugin, file transform, accessibility, compiled GUI replay).