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.
Borrowing it
Nothing to install: this file belongs to cloudflare/computer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cloudflare/computer/main/.agents/skills/prose/SKILL.mdgit 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/prose)<a href="https://agentmods.dev/skills/cloudflare/computer/prose"><img src="https://agentmods.dev/badge/skills/cloudflare/computer/prose/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/prose"><img src="https://agentmods.dev/badge/skills/cloudflare/computer/prose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00054 | $0.02652 |
| Opus 5.5 | $0.00022 | $0.01061 |
| Sonnet 5.5 | $0.00011 | $0.00530 |
| Haiku 4.5 | $0.00005 | $0.00265 |
Grade A, and why
prose 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 2mo 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prose
- IMPORTANT! Keep language simple. Use plain English.
- IMPORTANT! Avoid technical terms or jargon when a plain word will do.
- IMPORTANT! Avoid acronyms. Use the full word, e.g. "durable object" instead of "DO". Exceptions: established acronyms more common than their expansion, like "AI" or "API".
- IMPORTANT! Never insert marker comments in code or decorative characters in prose.
- IMPORTANT! Use American English at all times.
- IMPORTANT! Never refer to conversations, chat history, review threads, agents, or development sessions when writing plans, documentation, commits, or pull requests. Stand-alone artifacts only.
Voice
- Talk like a human. Avoid corporate or startup speak. Write like an engineer talking to another engineer.
- Don't assume specialist knowledge. Engineers are sophisticated, but don't assume domain context they may not share.
- Be honest. Don't hide reality. If you're doing something for a reason, say so.
- Be clear. Do the hard work to help readers understand complex ideas.
- Be funny when it fits. Not exclusionary "you had to be there" humor — Simpsons humor, where the joke doesn't get in the way for readers who don't catch it.
- Use active voice. "We will listen to your complaint", not "Your complaint will be listened to". Passive voice is fine when it reads more naturally, e.g. "Starting today, the per-second price is cut in half."
- Talk directly to "you", the reader.
- Don't overuse exclamation points. They lose their force when every other line ends in one.
Word choice
- Prefer simple verbs.
- "improve" not "revolutionize"
- "use" not "leverage" or "utilize"
- "help" not "assist"
- "let" not "enable"
- "make sure" not "ensure"
- "turn off" or "shut down" not "sunset"
- Prefer verbs to nouns. "We help users", not "We provide help to users".
- Drop adverbs that don't add information. "thousands of models", not "thousands of incredible models".
- Avoid words like "easy", "simply", "just". They imply the reader is slow when they get stuck.
- Avoid ableist and exclusionary terms like "crazy" or "lame".
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.
- 2mo ago First seen · 288 lines · 54 tokens per session scan A ffb592d95f32
prose is a skill published in the GitHub repository cloudflare/computer (9,753 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 2,652 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…