Cloudflare Skills is a collection of instructions and tools that help coding agents build on Cloudflare Workers, the Agents SDK, and other Cloudflare developer services. It is for agents and developers using Cloudflare’s platform. The catalogue entries package the project’s guidance as skills, commands, rules, plugins, and MCP tools.
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.
git clone --depth 1 https://github.com/cloudflare/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/rules/cloudflare/skills/workers)<a href="https://agentmods.dev/rules/cloudflare/skills/workers"><img src="https://agentmods.dev/badge/rules/cloudflare/skills/workers/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/rules/cloudflare/skills/workers"><img src="https://agentmods.dev/badge/rules/cloudflare/skills/workers.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 | $0.00018 | $0.00376 |
| Opus 5.5 | $0.00007 | $0.00150 |
| Sonnet 5.5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
workers 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 15d 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.
What it actually says
Cloudflare Workers
Your knowledge of Cloudflare Workers APIs, types, and configuration may be outdated. Prefer retrieval over pre-training. Use the project's installed versions, generated types, and compatibility settings as the baseline. Retrieve relevant Cloudflare documentation to verify API, configuration, runtime behavior, and limit claims.
Workers Defaults
- Keep compatibility dates current. Use today's date for new Workers. Encourage periodic updates for existing Workers, reviewing compatibility changes and running relevant tests.
- Enable logs and traces. When creating or preparing a Worker for production, set
observability.enabledandobservability.traces.enabledtotrue. The top-level setting alone does not enable traces. Use structured JSON logging and configure sampling for the workload. During reviews, flag missing logs or traces. See Workers Logs and Traces. - Keep binding types in sync. Run
wrangler typesafter changing bindings in the project's Wrangler configuration, whether JSONC, JSON, or TOML.
Shared Guidance
- Use workers-best-practices for runtime patterns, anti-patterns, configuration, and platform API checks. Read the references relevant to the task.
- Use wrangler for CLI commands and deployment configuration.
- Find documentation for products used by the Worker in the Cloudflare docs directory. Verify limits and quotas against the affected product's documentation.
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.
- 15d ago Changed dd0f482da007
- 1mo ago Changed · -40 lines · +18 tokens per session fd3e372513d2
- 1mo ago Changed 06ccac0eed3f
- 1mo ago First seen · 61 lines · 0 tokens per session scan A b5443d6c57c0
workers is a cursor rule published in the GitHub repository cloudflare/skills (3,079 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 376 once invoked, about $0.0001 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 cursor rules, from other repositories
previews
Cloudflare Worker Previews pipeline - credential-free Preview build then cf previews deploy, cf previews delete, Wrangler-only secrets, Access before arming, agent loop.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).