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 j4flmao/agent-skills --skill cloudflare-workersgit clone --depth 1 https://github.com/j4flmao/agent-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/j4flmao/agent-skills/cloudflare-workers)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/cloudflare-workers"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/cloudflare-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/skills/j4flmao/agent-skills/cloudflare-workers"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/cloudflare-workers.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 | $0.00138 | $0.01707 |
| Opus 5.5 | $0.00055 | $0.00683 |
| Sonnet 5.5 | $0.00028 | $0.00341 |
| Haiku 4.5 | $0.00014 | $0.00171 |
Grade A, and why
cloud-native-cloudflare-workers 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 today.
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.
async fetch(req: Request, env: Env, ctx: ExecutionContext): Promise<Response> { How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Workers and V8 Isolates
Purpose
Run request-path logic close to users on Cloudflare's network. Workers use V8 isolates rather than per-function VMs or containers, which makes startup cheap but imposes a Web-standard runtime with CPU and memory limits; storage choice drives consistency and latency.
Agent Protocol
Trigger
"cloudflare workers", "v8 isolates", "edge function", "wrangler", "durable objects", "workers kv", "D1", "R2", "edge compute".
Input Context
- Workload: request rewriting/auth, API, full-stack app, websockets, scheduled jobs.
- Data needs: read-heavy config, relational queries, blobs, strongly consistent per-key state.
- Node.js library dependencies.
Output Artifact
wrangler.toml/wrangler.jsonc and Worker code. No file unless requested.
Response Format
Runtime fit: {ok|needs nodejs_compat|not a fit (why)}
Storage: {KV|D1|R2|Durable Objects|Queues|Hyperdrive} (why)
Consistency: {eventual|strong per object|...}
Limits to watch: {CPU ms, memory, subrequests}
Completion Criteria
- Storage primitive matches the consistency requirement.
- Bindings declared in wrangler config; secrets via
wrangler secret put. - No blocking/long CPU work in the request path.
Isolates vs MicroVMs
| V8 isolate (Workers) | MicroVM (Lambda/Firecracker) | |
|---|---|---|
| Unit of isolation | Isolate (separate heap) inside a shared runtime process, plus process-level sandboxing | Dedicated lightweight VM with its own guest kernel |
| Startup | Milliseconds; Cloudflare also pre-warms during the TLS handshake | Tens of ms to seconds depending on runtime and init code |
| Runtime | Web-standard APIs (fetch, Request, Response, Web Crypto, Streams) + optional Node.js compatibility |
Full OS process, any language/binary |
| Memory | 128 MB per isolate | Up to 10,240 MB |
| Good for | Latency-sensitive request handling, auth, routing, APIs | Heavy compute, native binaries, long jobs |
Containers do not boot a kernel — they share the host kernel; Lambda's cost comes from booting a microVM, starting the language runtime, and running init 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.
- today Changed · +120 lines · +138 tokens per session dba823e61494
- 1mo ago First seen · 33 lines · 0 tokens per session scan A f50826153e63
cloud-native-cloudflare-workers is a skill published in the GitHub repository j4flmao/agent-skills (34 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 1,707 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
Cloudflare Workers & Edge AI Development
Build ultra-low-latency edge computing applications with Cloudflare Workers, Workers AI for LLM inference, V8 isolates, Durable Objects, and serverless patterns deployed across 330+ data centers worldwide.
sandbox-stable
Build or maintain Cloudflare Sandbox apps on the stable @cloudflare/sandbox package. Use sandbox-next for preview apps and sandbox-migrate-to-next for stable-to-preview migrations.
sandbox-next
Build or maintain Cloudflare Sandbox apps on @cloudflare/sandbox@next (SDK 1.0 preview). Use sandbox-migrate-to-next when porting a stable app.
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
cloudflare
Discover and choose Cloudflare products for apps, APIs, AI agents, storage, networking, and security. Use for architecture and product selection, including when the user describes a need without naming a Cloudflare product; then find the relevant skill or documentation.
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.