Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/manaflow-ai/cmux-skillsnpx agentmods add skills/manaflow-ai/cmux-skills/cmux-browserWrote 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/manaflow-ai/cmux-skills/cmux-browser)<a href="https://agentmods.dev/skills/manaflow-ai/cmux-skills/cmux-browser"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-browser/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/manaflow-ai/cmux-skills/cmux-browser"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00055 | $0.01646 |
| Opus 5 | $0.00028 | $0.00823 |
| Sonnet 5 | $0.00011 | $0.00329 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
cmux-browser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux Browser
Use this skill for browser automation inside cmux webview surfaces. It is different from a standalone browser automation tool because every browser surface lives inside a cmux workspace, pane, and surface topology.
Default Rule
Open and control browser surfaces in the current caller workspace unless the user explicitly names another workspace or window.
Before mutating browser state, identify the caller:
printf 'workspace=%s\nsurface=%s\nsocket=%s\n' \
"${CMUX_WORKSPACE_ID:-}" \
"${CMUX_SURFACE_ID:-}" \
"${CMUX_SOCKET_PATH:-}"
cmux identify --json
Use CMUX_WORKSPACE_ID for new browser splits and CMUX_SURFACE_ID to understand the terminal that invoked the automation. Do not open a browser in the visually focused workspace if it differs from the caller workspace.
Core Workflow
# Open in the caller workspace and capture the returned surface ref.
cmux --json browser open https://example.com --workspace "${CMUX_WORKSPACE_ID:-}"
# Use the returned surface, for example surface:7.
cmux browser surface:7 get url
cmux browser surface:7 wait --load-state complete --timeout-ms 15000
cmux browser surface:7 snapshot --interactive --compact
cmux browser surface:7 click e2 --snapshot-after
cmux browser surface:7 snapshot --interactive --compact
Loop: navigate, verify URL, wait, snapshot, act, then re-snapshot. Snapshot refs are temporary. Re-snapshot after navigation, modal changes, tab changes, or DOM updates.
Targeting
Most subcommands require a browser surface:
cmux browser identify
cmux browser identify --surface surface:2
cmux browser surface:2 get url
cmux browser --surface surface:2 get title
Open commands can create or reuse a browser split:
cmux browser open http://localhost:3000 --workspace "${CMUX_WORKSPACE_ID:-}" --json
cmux browser open-split https://example.com --workspace workspace:2 --json
cmux browser new https://example.com --window window:1 --json
Keep one browser surface per task unless the user asks for multiple tabs or pages.
What ships with it
2 files 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.
- 12d ago First seen · 160 lines · 55 tokens per session scan A 5fe7357aefdc
cmux-browser is a skill published in the GitHub repository manaflow-ai/cmux-skills (31 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 1,646 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…