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 agentmods add commands/superbenefit/sb-marketplace/cf-devgit clone --depth 1 https://github.com/superbenefit/sb-marketplaceWrote 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.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00967 |
| Opus 5 | $0.00013 | $0.00483 |
| Sonnet 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 3d 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.
- 3d 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 7mo ago), licensed CC0-1.0. It adds 25 tokens to every session and 967 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 2026-08-31.
Other commands, from other repositories
deploy
Build, test, deploy with staged rollout.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
deploy
Build a container image, push it, and deploy the service to the Akka platform. This is the transition from local development to development on the AAO platform.
scan
Scan AWS account for cost optimization.
firebase-publish
Create or reuse a Firebase project, configure Hosting, and deploy the current static site. Never deletes.
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…