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 G1Joshi/Agent-Skills --skill cloudflaregit clone --depth 1 https://github.com/G1Joshi/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/g1joshi/agent-skills/cloudflare)<a href="https://agentmods.dev/skills/g1joshi/agent-skills/cloudflare"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/cloudflare/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/g1joshi/agent-skills/cloudflare"><img src="https://agentmods.dev/badge/skills/g1joshi/agent-skills/cloudflare.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 | $0.00019 | $0.00358 |
| Opus 5 | $0.00010 | $0.00179 |
| Sonnet 5 | $0.00004 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
cloudflare 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 6d 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
Cloudflare is more than a CDN; it is a global super-cloud. In 2025, Workers AI (Edge GPU inference) and R2 (Egress-free storage) are compelling reasons to build here.
When to Use
- Edge Compute: Cloudflare Workers start in <5ms globally. Perfect for APIs and Middleware.
- Storage: R2 is S3-compatible but has zero egress fees. Massive cost savings for data-heavy apps.
- Security: Zero Trust (Access) replaces corporate VPNs.
Core Concepts
Workers
V8 Isolate-based serverless functions. No cold starts. Write code in TS/JS/Rust/Python.
Durable Objects
Stateful storage at the edge. Allows coordination (e.g., waiting lists, chat rooms) globally without a central DB.
Workers AI
Run open-source models (Llama 3, Whisper) on Cloudflare's network of GPUs with a simple API call.
Best Practices (2025)
Do:
- Use Wrangler: The CLI is fantastic for local dev and deploy (
npx wrangler dev). - Use R2: Move high-bandwidth assets from AWS S3 to R2 to kill egress bills.
- Use Pages: For hosting static sites + functions (full stack JAMstack).
Don't:
- Don't block good bots: Configure WAF carefully. Use "Managed Rulesets" rather than writing brittle regex rules securely.
References
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.
- 6d ago First seen · 45 lines · 19 tokens per session scan A b0fb0ce0f5f8
cloudflare is a skill published in the GitHub repository G1Joshi/Agent-Skills (12 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 358 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
aws-serverless-eda
AWS serverless and event-driven architecture expert based on Well-Architected Framework. Use when building serverless APIs, Lambda functions, REST APIs, microservices, or async workflows.
telnyx-storage-curl
Manage cloud storage buckets and objects using the S3-compatible Telnyx Storage API. This skill provides REST API (curl) examples.
nodejs-codestyle
Custom Instructions: Node.js Backend & Architecture Expert.
php-laravel-codestyle
Custom Instructions: PHP 8+ & Laravel Architecture Expert.
prometheus-alertmanager
Write production-quality Prometheus alert rules, recording rules, and Alertmanager routing configs.