Cloudflare Computer is a virtual filesystem whose state is stored in SQLite inside a Durable Object and exposed through selectable execution backends. It lets coding agents work with files, shell commands, JavaScript modules, containers, and networked Linux environments.
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 cloudflare/computer --skill execgit clone --depth 1 https://github.com/cloudflare/computerWrote 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/cloudflare/computer/exec)<a href="https://agentmods.dev/skills/cloudflare/computer/exec"><img src="https://agentmods.dev/badge/skills/cloudflare/computer/exec/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/cloudflare/computer/exec"><img src="https://agentmods.dev/badge/skills/cloudflare/computer/exec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.00433 |
| Opus 5.5 | $0.00024 | $0.00173 |
| Sonnet 5.5 | $0.00012 | $0.00087 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
exec scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Debian, with `bash`, `git`, `curl` and the usual core tools. What it actually says
Running commands
Every exec call runs your command with bash in a Linux container.
The durable object starts the container, and a small daemon in it,
computerd, runs the command.
What's installed
- Debian, with
bash,git,curland the usual core tools. - Node.js 22 and
npm. - Anything else can be installed with
apt-getornpm. It lasts until the container stops.
Network
The container has direct network access, so npm install, git clone
and curl work.
Files
/workspacein the container is the workspace.cwddefaults to it.- The durable object's storage holds the authoritative copy. Before each
call, changes made outside the container are pushed into
/workspace. After the call, changes made in the container are pulled back. Something written outside/workspacestays in the container and isn't saved. /workspace/.agents/skills(where this file lives) is a read-only copy of files shipped with the Worker. Changes you make there in the container are dropped when the call ends.
Things to know
- The first call is slow, because the container has to boot. Later calls reuse it while it stays up.
- A container that stops loses everything outside
/workspace, including installed packages. Reinstall rather than assume they're still there. - Every file under
/workspaceis synced back to storage after each call. This example keeps no paths on the container's local disk, so a largenode_modulesor build folder under/workspaceslows every call down. Put throwaway output in/tmp.
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.
- 3d ago First seen · 47 lines · 60 tokens per session scan A 14deb5fc419c
exec is a skill published in the GitHub repository cloudflare/computer (9,607 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 433 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.
managing-astro-local-env
Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.
polar-local-environment
This skill should be used when setting up or managing Polar local development environment with Docker.