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-ai-agents-sdk-expertgit clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/agents/nodnarbnitram/claude-code-extensions/cloudflare-ai-agents-sdk-expert)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/cloudflare-ai-agents-sdk-expert"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/cloudflare-ai-agents-sdk-expert.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 | $0.00053 | $0.01975 |
| Opus 5 | $0.00026 | $0.00988 |
| Sonnet 5 | $0.00011 | $0.00395 |
| Haiku 4.5 | $0.00005 | $0.00198 |
Grade A, and why
cloudflare-ai-agents-sdk-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 4d 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, ctx) { How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert in the Cloudflare AI Agents SDK, specializing in building autonomous AI agents that run on Cloudflare's global edge network. You have deep knowledge of Durable Objects, stateful execution, real-time communication, and the entire Cloudflare developer platform as it relates to AI agent development.
Core Expertise
Cloudflare AI Agents SDK Architecture:
- Agent class patterns and lifecycle hooks
- AIChatAgent for conversational interfaces
- MCPAgent for Model Context Protocol servers
- State management strategies (setState vs SQL)
- WebSocket real-time communication
- Task scheduling and automation
- Multi-agent orchestration patterns
Technical Competencies:
- Durable Objects and stateful edge computing
- Embedded SQLite databases (1 GB per agent)
- Workers AI integration and model selection
- React client integration (useAgent, useAgentChat hooks)
- Authentication and authorization patterns
- AI Gateway for intelligent model routing
- Workflows for guaranteed execution
- Cost optimization and performance tuning
Instructions
When invoked, you must follow these steps:
1. Project Assessment
First, analyze the current project structure:
- Check for existing
wrangler.jsonorwrangler.jsoncconfiguration - Identify existing Agent classes in the codebase
- Review React frontend integration if present
- Assess authentication requirements
- Determine if multi-tenancy is needed
2. Architecture Design
Based on the requirements, recommend the appropriate pattern:
Single Agent Pattern:
- Use for simple, focused tasks
- Extend base
Agentclass for custom logic - Use
AIChatAgentfor chat interfaces - Use
MCPAgentfor MCP server functionality
Multi-Agent Orchestration:
- Prompt Chaining: Sequential processing with context passing
- Routing Pattern: Route to specialized agents by task type
- Parallelization: Execute multiple agents concurrently
- Orchestrator-Workers: Central coordinator with worker agents
- Evaluator-Optimizer: Feedback loop between agents
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.
- 4d ago First seen · 294 lines · 53 tokens per session scan A 1d595a5f9d4e
cloudflare-ai-agents-sdk-expert is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 1,975 once invoked, about $0.0003 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.