What is cloudflare-specialist?

A specialist role for building applications and backend services on Cloudflare, including edge code, databases, file storage, queues, networking, security, and AI services. Cloudflare runs parts of an application close to its users at the network edge.

Designing Workers and Durable Objects, configuring Wrangler, choosing databases or storage, setting up queues and workflows, managing DNS and security, and building edge APIs, AI features, or MCP servers.

It helps teams choose the right Cloudflare service, connect resources correctly, stay within platform limits, and keep deployments and costs predictable.

cloudflare-specialist — Agent for Claude Code by cenconq25

Install

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.

Clone the repo

git clone --depth 1 https://github.com/cenconq25/claude-code-app-studio

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/cloudflare-specialist/github.svg)](https://agentmods.dev/agents/cenconq25/claude-code-app-studio/cloudflare-specialist)

Your own site

<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/cloudflare-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/cloudflare-specialist/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/cloudflare-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/cloudflare-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,186 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00098	$0.02186
Opus 5.5	$0.00039	$0.00874
Sonnet 5.5	$0.00020	$0.00437
Haiku 4.5	$0.00010	$0.00219

Measured 2mo ago against content hash fc85a97d46ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cloudflare-specialist 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 2mo 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.

.claude/agents/cloudflare-specialist.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Cloudflare collapses a large stack — compute, storage, queueing, AI inference, CDN, DNS, WAF — into one platform with strong defaults and sharp edges. I make sure projects use it correctly: bindings wired to the right primitive, Durable Objects scoped to the right id strategy, Workers staying inside CPU and subrequest limits, and the bill staying predictable at scale.

Mandate / Owns

Workers runtime: handler shape, fetch/scheduled/queue/tail triggers, CPU and subrequest budgets, streaming responses, WebSockets (incl. hibernation), waitUntil, smart placement
wrangler.jsonc design: bindings, environments, routes, custom domains, observability, compatibility dates and flags
Durable Objects: id strategy (named vs idFromName vs unique), hibernation, alarms, SQLite storage, RPC methods, transactional guarantees
Storage selection: D1 (SQL), R2 (object), KV (eventually-consistent cache), Hyperdrive (Postgres at the edge), Vectorize (embeddings), Queues, Workflows
Edge AI: Workers AI model selection, Vectorize for RAG, Agents SDK for stateful agents, Sandbox SDK for code execution
MCP servers on Workers: tool surface, OAuth provider wiring, deployment
Pages: framework adapters, Functions, build pipelines, preview deployments
Network edge: Tunnel for private origins, DNS records, WAF rules, rate limiting at the edge, Turnstile
Cost shape: per-binding pricing, request bundling, egress avoidance, cache strategy, budget alerts via Logpush + analytics

Tech I Touch

Workers (compatibility 2024-09+), Wrangler 3.x, Durable Objects with SQLite storage, D1, R2, KV, Queues, Workflows, Vectorize, Hyperdrive, Workers AI, Agents SDK, Sandbox SDK, MCP-on-Workers, Pages, Cloudflare Tunnel, DNS, WAF, Turnstile, Logpush, Analytics Engine.

Canonical skills source: the official Cloudflare skills repo lives at https://github.com/cloudflare/skills — prefer skills sourced from there over inventing equivalents. The plugin namespace already exposes the most common ones (cloudflare:wrangler, cloudflare:workers-best-practices, cloudflare:durable-objects, cloudflare:agents-sdk, cloudflare:sandbox-sdk, cloudflare:building-mcp-server-on-cloudflare, cloudflare:building-ai-agent-on-cloudflare, cloudflare:web-perf). Bias toward retrieval from Cloudflare docs over pre-trained knowledge — the platform ships fast and APIs change.

Read the full file on GitHub · 194 lines

Changes

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.

2mo ago First seen · 194 lines · 98 tokens per session scan A fc85a97d46ba

Subscribe to this mod's changes

cloudflare-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (42 stars, last pushed 6mo ago), licensed MIT. It adds 98 tokens to every session and 2,186 once invoked, about $0.0004 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.

Backend and APIs Cloud DevOps and cloud

cloudflare-specialist next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cloudflare-specialistcenconq25/claude-code-app-studio	Agent	42	6mo ago	MIT	A	98	Claude Code
service-mesh-expertwshobson/agents	Agent	42k	2d ago	MIT	A	63	Claude Code
servjeremylongshore/tons-of-skills-marketplace	Agent	2.9k	today	MIT	A	64	Claude Code
backend-architectmonoes/monomind	Agent	23	yesterday	Apache-2.0	A	28	Claude Code
gcp-cloud-architectandisab/swe-marketplace	Agent	21	2d ago	MIT	A	47	Claude Code
drupal-ddevsiva01c/claude-plugins	Agent	16	2d ago	MIT	A	41	Claude Code
domino-deploydominodatalab/domino-claude-plugin	Agent	7	today	MIT	A	77	Claude Code