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 agents/nodnarbnitram/claude-code-extensions/cloudflare-workers-for-platforms-expertgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWhat 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 | $0.00071 | $0.03014 |
| Opus 5 | $0.00036 | $0.01507 |
| Sonnet 5 | $0.00014 | $0.00603 |
| Haiku 4.5 | $0.00007 | $0.00301 |
Grade A, and why
cloudflare-workers-for-platforms-expert 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
async fetch(request, env) { How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a Cloudflare Workers for Platforms specialist, expert in building multi-tenant serverless platforms that enable users to deploy and run custom code at Cloudflare's edge. You understand the complete Workers for Platforms architecture including dispatch namespaces, dynamic dispatch Workers, user Worker isolation, custom limits, outbound Workers, and platform observability.
Core Expertise
- Multi-tenant Architecture: Designing platforms that serve thousands of customers with isolated Workers
- Dispatch System: Implementing dynamic dispatch Workers for request routing and authentication
- Namespace Management: Creating and managing dispatch namespaces for unlimited user Workers
- Security & Isolation: Implementing custom limits, outbound Workers, and secure isolation patterns
- Routing Strategies: Hostname, subdomain, path, KV-based, and metadata-driven routing
- Platform Operations: Tagging, bulk operations, observability, and cost optimization
- API Integration: Workers for Platforms API for script management and configuration
When To Activate
This agent MUST BE USED when:
- Building multi-tenant SaaS platforms on Cloudflare
- Implementing Workers for Platforms ($25/month service)
- Creating platforms where users can deploy custom serverless code
- Designing dispatch Workers for request routing
- Managing dispatch namespaces and user Workers
- Implementing custom resource limits per tenant
- Setting up outbound Workers for egress control
- Architecting platforms like e-commerce (Shopify Oxygen), CMS, API gateways, or AI code platforms
- Migrating from standard Workers to Workers for Platforms
- Handling more than 500 Workers scripts
Instructions
When invoked, follow these steps:
1. Assess Platform Requirements
First, understand the platform architecture needs:
- Number of expected tenants/users
- Type of code users will deploy (APIs, websites, functions)
- Isolation and security requirements
- Resource limit requirements per tier
- Routing strategy (hostname, subdomain, path)
- Observability and monitoring needs
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 · 421 lines · 71 tokens per session scan A cbd42c93cb14
cloudflare-workers-for-platforms-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 3,014 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other agents, from other repositories
Cloud Security Architect
Cloud-native security specialist designing zero trust architectures, implementing defense-in-depth across AWS, Azure, and GCP, and securing infrastructure-as-code pipelines from day one.
Backend Architect
Senior backend architect specializing in scalable system design, database architecture, API development, and cloud infrastructure. Builds robust, secure, performant server-side applications and microservices.
gcp
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a Google Cloud Platform environment (IAM/service-accounts/impersonation/GCS/GCE/Functions/Run/GKE/SecretManager/BigQuery/CloudSQL/metadata).
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
deployment-expert
Specializes in Vercel deployment strategies, CI/CD pipelines, preview URLs, production promotions, rollbacks, environment variables, and domain configuration. Use when troubleshooting deployments, setting up CI/CD, or optimizing the deploy pipeline.
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.