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 manaflow-ai/cmux-skills --skill cmux-refgit clone --depth 1 https://github.com/manaflow-ai/cmux-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/manaflow-ai/cmux-skills/cmux-ref)<a href="https://agentmods.dev/skills/manaflow-ai/cmux-skills/cmux-ref"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-ref/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-ref"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-ref.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- 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 | $0.00057 | $0.01216 |
| Opus 5 | $0.00028 | $0.00608 |
| Sonnet 5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
cmux-ref 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux Ref
Use this skill when the user pastes cmux topology identifiers and expects the agent to target that exact workspace, pane, surface, or window. Treat those identifiers as explicit routing context for later instructions.
What To Recognize
Users may paste any mix of these fields, in plain text, Markdown, JSON, YAML, shell-style assignments, or logs:
workspace_ref=workspace:1
workspace_id=D9C23F06-55C8-4EF6-96D2-F2531B3327A8
pane_ref=pane:2
pane_id=60495E4A-56E3-469D-A274-A7877F48B54D
surface_ref=surface:370
surface_id=661B301A-2423-44F1-B789-7AEA1021CFCE
Recognize these keys:
window_ref,window_idworkspace_ref,workspace_idpane_ref,pane_idsurface_ref,surface_id
Also recognize bare refs near user intent, such as workspace:1, pane:2, or surface:370.
Meaning
*_refvalues are short cmux refs such asworkspace:1,pane:2, andsurface:370. They are convenient for immediate CLI calls in the same cmux instance, but can be renumbered after state changes.*_idvalues are UUIDs for the same objects. Prefer them for identity checks and stale-ref recovery when both forms are available.- The most specific provided object is the default target:
surfacebeatspane,panebeatsworkspace, andworkspacebeatswindow. - A complete block describes a hierarchy. Do not mix a
surface_idfrom one pasted block with aworkspace_reffrom another unless the user clearly says they belong together.
Workflow
Step 1: Parse The Block
Extract keys case-insensitively. Accept = or : separators and ignore quotes, commas, and code fences.
Useful pattern:
\b(window|workspace|pane|surface)_(ref|id)\b\s*[:=]\s*["']?([A-Za-z0-9:-]+)["']?
If the user provides only bare refs, bind the most specific one as the target:
workspace:1 pane:2 surface:370
Step 2: Announce The Target
When taking action, say the exact target briefly:
I will target surface:370 in pane:2, workspace:1.
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.
- 11d ago First seen · 117 lines · 57 tokens per session scan A 40fceb04b257
cmux-ref is a skill published in the GitHub repository manaflow-ai/cmux-skills (31 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 1,216 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
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…