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 skills add glebis/claude-skills --skill cmuxgit clone --depth 1 https://github.com/glebis/claude-skillsWrote 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/glebis/claude-skills/cmux)<a href="https://agentmods.dev/skills/glebis/claude-skills/cmux"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/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/glebis/claude-skills/cmux"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/cmux.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.02877 |
| Opus 5.5 | $0.00000 | $0.01151 |
| Sonnet 5.5 | $0.00000 | $0.00575 |
| Haiku 4.5 | $0.00000 | $0.00288 |
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 1mo 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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux
Controls the cmux macOS terminal app via its CLI socket API to orchestrate workspaces, panes, browser previews, sidebar status, and notifications.
Full CLI reference: references/api_reference.md
Quick Check
Always verify cmux is running before issuing commands:
cmux ping 2>/dev/null && echo "ok" || echo "cmux not available"
If unavailable, skip cmux enhancements silently — never block the main task.
Core Use Cases
1. Auto Preview Routing
When a dev server starts or an HTML file is created, open it in a right-side browser pane:
# Dev server detected (e.g. localhost:3000)
cmux new-pane --type browser --direction right --url http://localhost:3000
# HTML file created — serve it first, then preview
cd <project-dir> && python3 -m http.server 8080 &
cmux new-pane --type browser --direction right --url http://localhost:8080/<file>.html
When to trigger:
- Output contains
localhost:PORT,127.0.0.1:PORT,Server running,Listening on - A
.htmlfile is written and the user would benefit from seeing it rendered - superpowers or another skill opens a visual artifact
Direction heuristic: right for wide layouts, down for narrow/tall terminals.
2. Subagent Workspaces
When dispatching parallel agents (via superpowers:dispatching-parallel-agents or similar), give each agent its own named cmux workspace so it's visible in the sidebar:
# Create a workspace per agent (new-workspace has no --cwd — cd inside --command)
cmux new-workspace --command "cd /path/to/project && claude --dangerously-skip-permissions"
cmux rename-workspace "agent: fix-auth"
# Set status so the sidebar shows what the agent is doing
cmux set-status task "fix-auth" --icon "⚡"
cmux set-status state "running" --color "#F59E0B"
When an agent completes:
cmux notify --title "Agent done" --subtitle "fix-auth" --body "Merged and cleaned up"
cmux set-status state "done" --color "#10B981"
Pattern: workspace 1 = orchestrator, workspaces 2–8 = subagents. Use cmux list-workspaces --json to track IDs.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 289 lines · 0 tokens per session scan A 08b637f28d04
cmux is a skill published in the GitHub repository glebis/claude-skills (400 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,877 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 2026-09-03.
Other skills, from other repositories
Webdesign
Design and integrate web interfaces via three paths: DirectDesign (write design inline with Anthropic frontend-design philosophy — the default workhorse), native /design + /design-sync Claude Code commands (preferred for code integration and design-system sync), or ClaudeDesign (drive claude.ai/design through…
ui-ux-pro-max
Use when planning, building, designing, code review, refactor, fixing, improving, optimizing, enhancing, or checking UI/UX work. Covers product patterns, landing pages, chart choices, visual styles, palettes, typography, UX rules, and 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind…
ui-design-system
Use when creating or maintaining UI design systems, design tokens, component documentation, responsive calculations, quality checks, or design-dev handoff materials.
web-design-expert
Web design and UX guidance for visual systems, accessibility, interaction patterns, and performance-aware interfaces. Use when designing a website's look and feel, improving UX/accessibility, or reviewing a UI for polish and performance.
core-web-vitals
Measure and hold a real performance budget on a web page — LCP, INP, CLS, bundle weight, font and image loading. Use when a change touches images, fonts, above-the-fold markup, client components, third-party scripts, or any list that can grow; when a page feels slow; or before shipping a new landing page or hero.…
visual-proof
Capture before/after screenshot evidence of a web page at real breakpoints (375, 768, 1440) in both light and dark themes, using Playwright against a local dev server or a deployed URL. Use before starting any visual change to capture the current state, and again after to prove the delta. Also use when asked to "show…