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-freestylegit 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-freestyle)<a href="https://agentmods.dev/skills/manaflow-ai/cmux-skills/cmux-freestyle"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-freestyle/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-freestyle"><img src="https://agentmods.dev/badge/skills/manaflow-ai/cmux-skills/cmux-freestyle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk fail
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 | $0.00104 | $0.03037 |
| Opus 5 | $0.00052 | $0.01519 |
| Sonnet 5 | $0.00021 | $0.00607 |
| Haiku 4.5 | $0.00010 | $0.00304 |
Grade D, and why
cmux-freestyle scanned grade D with 3 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/manaflow-ai/cmux-freestyle/main/install.sh | bash Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `enter` opens the **sandbox** workflow: creates a new cmux workspace running `freestyle-vm-ssh <vmId>`. The helper script mints a short-lived Freestyle SSH identity, opens an SSH session through `vm-ssh.freestyle.sh` w Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/manaflow-ai/cmux-freestyle/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cmux Freestyle
Use this skill when a user wants a Freestyle VM snapshot that the cmux backend can boot Cloud VMs from. It lives in its own public repo, manaflow-ai/cmux-freestyle, so anyone with a Freestyle API key can run one shell script and get back a FREESTYLE_SANDBOX_SNAPSHOT id.
Freestyle snapshots are scoped to the account that created them. A snapshot id from manaflow's account, or from any other user, will not work for a different Freestyle account. Every user has to run the setup script against their own FREESTYLE_API_KEY. There is no shortcut.
When to use
- User asks how to point their own cmux at Freestyle.
- User self-hosts the cmux web backend and needs a snapshot pinned to a known cmux release.
- User wants to rebuild the cmux Cloud VM image on their own Freestyle account.
- User wants to iterate on the standalone repo (
cmux-freestyle) instead of the in-repo builder atrepo/web/scripts/build-cloud-vm-images.ts.
For internal cmux development that pushes a new snapshot to manaflow's Freestyle account and updates repo/web/services/vms/images/manifest.json, keep using repo/web/scripts/build-cloud-vm-images.ts. This skill is the external-user path.
What it builds
A Freestyle snapshot from a Dockerfile that mirrors freestyleBaseDockerfileContent in the in-repo builder:
ubuntu:24.04,C.UTF-8, the same shell package set, the Python/OpenSSL shim required by the cmux browser proxy.cmuxd-remoteLinux/amd64 downloaded from a pinnedmanaflow-ai/cmuxGitHub release, SHA-256 verified during the image build againstcmuxd-remote-checksums.txt./usr/local/bin/cmuxsymlinked tocmuxd-remote.- Node.js, Bun, plus pinned coding agent CLIs (Claude Code, OpenCode, Codex, Pi).
- Linux user
cmuxwith passwordless sudo. - Systemd unit
cmuxd-ws.servicerunningcmuxd-remote serve --ws --listen 0.0.0.0:7777 --auth-lease-file ... --rpc-auth-lease-file ...on Freestyle port443 -> 7777.
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 · 150 lines · 104 tokens per session scan D 3970cb1a658e
cmux-freestyle is a skill published in the GitHub repository manaflow-ai/cmux-skills (32 stars, last pushed 4d ago), licensed MIT. It adds 104 tokens to every session and 3,037 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). 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…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
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".
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…