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-cloudgit 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-cloud)<a href="https://agentmods.dev/skills/manaflow-ai/cmux-skills/cmux-cloud"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-cloud/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-cloud"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-cloud.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 8 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00080 | $0.01945 |
| Opus 5 | $0.00040 | $0.00972 |
| Sonnet 5 | $0.00016 | $0.00389 |
| Haiku 4.5 | $0.00008 | $0.00194 |
Grade A, and why
cmux-cloud 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux Cloud
Drive cmux Cloud machines (user-owned persistent Linux VMs) through the cmux CLI: create and attach, run commands and coding agents, move files, open ports and desktops, snapshot/fork/restore, and send notifications from inside a machine. Full per-command syntax lives in references/commands.md; cmux vm <sub> --help on the installed build is authoritative when they disagree.
Mental model
- A machine is a persistent cloud VM owned by the signed-in cmux user. Its generated name (
brave-otter) is its address everywhere;cmux vm renamesets a display label only. The cloud backend picks the provider; the machine outlives your panes, your Mac being closed, and reconnects. - Every machine runs a cmux session daemon (cmux-tui on current images, cmuxd-remote on older ones) that owns terminal sessions and scrollback. Clients (Mac panes, iOS) attach through short-lived leases minted by the backend; the transport depends on what the provider and image support. SSH is a fallback some providers and images cannot mint at all, and its absence is not an error.
- New machines boot a desktop image (xfce + noVNC) plus a shell, with a persistent per-machine home.
--basegives a shell-only machine. - Base is a separate single per-user persistent slot, pinned to the top of the sidebar.
vm newmints fresh machines;vm basealways reopens the same one. - Terminals on a machine live in its cmux-tui session (workspaces
ws_…, terminalsterm_…). They keep running detached;cmux vm treecatalogs every surface (local and cloud) and every line is an addresscmux vm open(machine targets) orcmux surface open(any entry, including This Mac) accepts, e.g.brave-otter/main/term_2f9c…,brave-otter:desktop,brave-otter:port/3000. - Pool machines (labeled
agent-poolinvm ls) are provisioned by thevm run/vm agentrouter and reused for routed work. The router never drafts machines a person made by hand. - Plans cap active machine count and memory.
cmux vm lsprints the meter (N of M machines on the <plan> plan) and, on free plans, when free cloud access expires.
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 · 103 lines · 80 tokens per session scan A 9d9a5855fb34
cmux-cloud is a skill published in the GitHub repository manaflow-ai/cmux-skills (31 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 1,945 once invoked, about $0.0004 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
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…