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 agentmods add skills/cloudflare/computer/pull-requestsnpx skills add cloudflare/computer --skill pull-requestsgit clone --depth 1 https://github.com/cloudflare/computerWhat 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 | $0.00038 | $0.01367 |
| Opus 5 | $0.00019 | $0.00683 |
| Sonnet 5 | $0.00008 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
pull-requests 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request + Merge Request Style Guide
Overview
A good pull request description is a Markdown document that tells the story of the accompanying git diff. It is intended for human consumption and should use plain language, read clearly and be easy to follow.
When to Use
Use this skill any time you are tasked with creating a pull request on GitHub. The output will be a markdown document that follows the style guide and meets the accompanying verification.
Structure
A good pull request tells the story of the change and is intended to add color and context that is not or cannot be conveyed in the source code.
It should aim to be concise and use paragraphs and prose where appropriate rather than bullet points to improve readability and tell the story. Bullet points can be used for lists when semantically appropriate.
Code examples and diagrams (using mermaid) are preferred over prose to communicate your message.
It should use the following structure and include a paragraph on each topic.
- Detail the problem the change is solving. Reference issues, PRs or documents if relevant.
- Explain the solution and how it solves the problem.
- Explain how the reader can manually verify the change. e.g. give a code example or a command to run locally.
- Document the testing strategy when applicable.
- Document any changes to documentation or READMEs that cover the changes.
- Document any follow up code changes required.
Any sections that are not relevant should be omitted.
Style guide
It is important to follow these rules when writing a pull request description.
At all times keep the use of language simple. Use plain English
Good: Clear
We've updated the
readFile()method to support streaming data so that the caller can read a file without buffering content into memory.
Bad: Verbose and technical jargon
The
readFile()function has an overload that when used returns aReadableStream()object that emits chunks ofUInt8Arraytype that can be used by the caller to stream bytes instead of base64 strings which are held in memory.
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.
- 2d ago First seen · 135 lines · 38 tokens per session scan A d1f8e96e3d5b
pull-requests is a skill published in the GitHub repository cloudflare/computer (8,834 stars, last pushed 4d ago), licensed MIT. It adds 38 tokens to every session and 1,367 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…