Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add superbenefit/sb-marketplace/plugin install cloudflare-devWrote 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/commands/superbenefit/sb-marketplace/cf-dev)<a href="https://agentmods.dev/commands/superbenefit/sb-marketplace/cf-dev"><img src="https://agentmods.dev/badge/commands/superbenefit/sb-marketplace/cf-dev/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/commands/superbenefit/sb-marketplace/cf-dev"><img src="https://agentmods.dev/badge/commands/superbenefit/sb-marketplace/cf-dev.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 | $0.00025 | $0.00967 |
| Opus 5.5 | $0.00010 | $0.00387 |
| Sonnet 5.5 | $0.00005 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00097 |
Grade A, and why
cf-dev 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Development Workflow
You are working on a Cloudflare project. Follow this workflow for all implementation tasks.
Step 1: Load Context
Read the relevant reference file(s) from the cloudflare-knowledge skill based on the task:
| Task Type | Reference File | Key Focus |
|---|---|---|
| Agent class, state, WebSocket | agents-sdk.md |
new_sqlite_classes in migrations |
| AI agent design patterns | agent-patterns.md |
Pattern selection guide |
| MCP server or client | agents-mcp.md |
createMcpHandler (recommended) |
| Vector search, RAG, embeddings | vectorize.md |
topK limits per returnMetadata |
| Durable execution, retries | workflows.md |
Always await step.do() |
| Workers, R2, KV, D1, bindings | workers-platform.md |
Use bindings, not REST API |
| OAuth, CI/CD, secrets, deploys | auth-deployment.md |
workers-oauth-provider patterns |
| Logs, traces, analytics | observability.md |
observability: { enabled: true } |
Reference files are located at: ${CLAUDE_PLUGIN_ROOT}/skills/cloudflare-knowledge/references/
Step 2: Verify with Cloudflare Docs MCP
Before implementing any pattern, verify the current API against the cloudflare-docs MCP server:
Recommended MCP queries by task:
- Agents:
"Agents SDK Agent class API","Agents SDK state management" - MCP servers:
"createMcpHandler MCP server","workers-oauth-provider" - Storage:
"R2 Workers API put get","KV Workers API","D1 prepared statements" - Vectorize:
"Vectorize query API topK","Workers AI reranker" - Workflows:
"Workflows step.do","Workflows waitForEvent" - Observability:
"Workers observability traces","Analytics Engine writeDataPoint" - Deployment:
"Workers Builds","wrangler secret"
Step 3: Implement
Follow the validated patterns from Steps 1-2. Apply these critical standards to ALL code:
Mandatory Configuration (wrangler.jsonc)
{
"compatibility_date": "2025-03-07", // Minimum for Agents
"compatibility_flags": ["nodejs_compat"],
"observability": { "enabled": true }
}
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 · 84 lines · 25 tokens per session scan A d9e094975fe3
cf-dev is a command published in the GitHub repository superbenefit/sb-marketplace (5 stars, last pushed 8mo ago), licensed CC0-1.0. It adds 25 tokens to every session and 967 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 2026-08-31.
Other commands, from other repositories
cost-optimize
Reduce cloud costs across AWS, Azure, and GCP through rightsizing, reserved and spot capacity, storage tuning, and cost monitoring.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
env
Manage Vercel environment variables. Commands include list, pull, add, remove, and diff. Use to sync environment variables between Vercel and your local development environment.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
scan
Scan AWS account for cost optimization.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…