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 agentmods add skills/manaflow-ai/cmux/cmux-browsernpx skills add manaflow-ai/cmux --skill cmux-browsergit clone --depth 1 https://github.com/manaflow-ai/cmuxWhat 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 | $0.00038 | $0.01021 |
| Opus 5 | $0.00019 | $0.00511 |
| Sonnet 5 | $0.00008 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
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 yesterday.
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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
10 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.
- agents/openai.yaml 327 B
- references/authentication.md 2.8 KB
- references/commands.md 5.1 KB
- references/proxy-support.md 579 B
- references/session-management.md 1.2 KB
- references/snapshot-refs.md 1.0 KB
- references/video-recording.md 940 B
- templates/authenticated-session.sh 555 B runs code
- templates/capture-workflow.sh 377 B runs code
- templates/form-automation.sh 360 B runs code
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.
- yesterday First seen · 85 lines · 38 tokens per session scan A 741d9941a3d6
cmux-browser is a skill published in the GitHub repository manaflow-ai/cmux (26,602 stars, last pushed yesterday), with no licence file. It adds 38 tokens to every session and 1,021 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
zentty-cli
Use when an agent is running inside Zentty or needs to discover panes, split or grid layouts, focus panes, launch nested coding agents, or notify the user through the Zentty CLI.
computer-use
Use Orca's computer-use CLI to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions. Use for desktop app interaction: list apps/windows, get app state, read visible UI, click controls, type, press keys, scroll, drag, set values, or perform accessibility actions.…
orca-cli
Use the public orca CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude…
plannotator
Reference for using the Plannotator CLI: plan review, code review, annotating files, URLs, folders, and running local apps, annotating the last assistant message, browsing archived plan decisions, and exporting or sharing Guided Reviews. Invoke when asked to use Plannotator for anything not covered by a more specific…
plannotator-review
Open Plannotator's browser-based code review UI and address the returned feedback.
agtx-sweep
Sweep this conversation into agtx tasks and push them to the kanban board. Use when the user wants to capture, decompose, or hand off conversation results to the agtx board.