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 secondsky/claude-skills --skill cloudflare-workers-performancegit clone --depth 1 https://github.com/secondsky/claude-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/secondsky/claude-skills/cloudflare-workers-performance)<a href="https://agentmods.dev/skills/secondsky/claude-skills/cloudflare-workers-performance"><img src="https://agentmods.dev/badge/skills/secondsky/claude-skills/cloudflare-workers-performance/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/secondsky/claude-skills/cloudflare-workers-performance"><img src="https://agentmods.dev/badge/skills/secondsky/claude-skills/cloudflare-workers-performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00042 | $0.01451 |
| Opus 5.5 | $0.00017 | $0.00580 |
| Sonnet 5.5 | $0.00008 | $0.00290 |
| Haiku 4.5 | $0.00004 | $0.00145 |
Grade A, and why
cloudflare-workers-performance 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 1mo 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Workers Performance Optimization
Techniques for maximizing Worker performance and minimizing latency.
Quick Wins
// 1. Avoid unnecessary cloning
// ❌ Bad: Clones entire request
const body = await request.clone().json();
// ✅ Good: Parse directly when not re-using body
const body = await request.json();
// 2. Use streaming instead of buffering
// ❌ Bad: Buffers entire response
const text = await response.text();
return new Response(transform(text));
// ✅ Good: Stream transformation
return new Response(response.body.pipeThrough(new TransformStream({
transform(chunk, controller) {
controller.enqueue(process(chunk));
}
})));
// 3. Cache expensive operations
const cache = caches.default;
const cached = await cache.match(request);
if (cached) return cached;
Critical Rules
- Stay under CPU limits - 10ms (free), 30ms (paid), 50ms (unbound)
- Minimize cold starts - Keep bundles < 1MB, avoid dynamic imports
- Use Cache API - Cache responses at the edge
- Stream large payloads - Don't buffer entire responses
- Batch operations - Combine multiple KV/D1 calls
Top 10 Performance Errors
| Error | Symptom | Fix |
|---|---|---|
| CPU limit exceeded | Worker terminated | Optimize hot paths, use streaming |
| Cold start latency | First request slow | Reduce bundle size, avoid top-level await |
| Memory pressure | Slow GC, timeouts | Stream data, avoid large arrays |
| KV latency | Slow reads | Use Cache API, batch reads |
| D1 slow queries | High latency | Add indexes, optimize SQL |
| Large bundles | Slow cold starts | Tree-shake, code split |
| Blocking operations | Request timeouts | Use Promise.all, streaming |
| Unnecessary cloning | Memory spike | Only clone when needed |
| Missing cache | Repeated computation | Implement caching layer |
| Sync operations | CPU spikes | Use async alternatives |
CPU Optimization
Profile Hot Paths
async function profiledHandler(request: Request): Promise<Response> {
const timing: Record<string, number> = {};
const time = async <T>(name: string, fn: () => Promise<T>): Promise<T> => {
const start = Date.now();
const result = await fn();
timing[name] = Date.now() - start;
return result;
};
const data = await time('fetch', () => fetchData());
const processed = await time('process', () => processData(data));
const response = await time('serialize', () => serialize(processed));
console.log('Timing:', timing);
return new Response(response);
}
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/bundle-optimization.md 8.5 KB
- references/caching-strategies.md 11 KB
- references/cold-starts.md 9.2 KB
- references/cpu-optimization.md 9.5 KB
- references/memory-optimization.md 9.7 KB
- scripts/benchmark.sh 12 KB runs code
- scripts/profile-worker.sh 12 KB runs code
- templates/caching-layer.ts 13 KB runs code
- templates/optimized-worker.ts 9.6 KB runs code
- templates/performance-middleware.ts 11 KB runs code
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.
- 1mo ago First seen · 218 lines · 42 tokens per session scan A 4d5886c3c9f5
cloudflare-workers-performance is a skill published in the GitHub repository secondsky/claude-skills (231 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,451 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 2026-09-03.
Other skills, from other repositories
why
Work out whether a failure is your machine or your code before debugging either, using the environment this repository has declared and the dependency map. Use when a test, build or command fails and the cause is not obvious from the error.
decide
A reusable decision procedure, and a copyable prototype for the guard that encodes it — derive the population, set one threshold by what being wrong costs, name the offender, and break it once to prove it can fail. Use when writing a check, guard, gate or validation of any kind, or when deciding whether something is…
remember
Record why something is the way it is — a decision and its reasoning, a lesson that cost time, or a standing constraint. Use when the reasoning behind a choice would be expensive to reconstruct later.
bootstrap
Set up chamnan in this repository for the first time — build the architecture index, measure how well the code describes itself, fill in missing file comments, and record a baseline. Run once per repo.
milestone
Record a change that reshaped the repository — what moved, why it was worth doing, and which areas it touched. Use after a migration, a rewrite, or a decision that changed how part of the system works.
resume
Write down where this stretch of work stopped, so the next session continues instead of restarting. Use at the end of a working session, or when handing the repository to someone else.