secondsky/claude-skills / plugins/cloudflare-agents/skills/cloudflare-agents
cloudflare-agents
VerifiedBuild AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.7 KB |
| references/advanced-features.md | markdown | 13.5 KB |
| references/agent-api.md | markdown | 2.9 KB |
| references/configuration-guide.md | markdown | 3.1 KB |
| references/error-catalog.md | markdown | 275 B |
| references/http-sse-guide.md | markdown | 2.0 KB |
| references/mcp-integration.md | markdown | 2.7 KB |
| references/patterns-concepts.md | markdown | 11.0 KB |
| references/state-management.md | markdown | 9.5 KB |
| references/websockets-guide.md | markdown | 3.0 KB |
| templates/basic-agent.ts | script | 383 B |
| templates/browser-agent.ts | script | 4.9 KB |
| templates/calling-agents-worker.ts | script | 3.7 KB |
| templates/chat-agent-streaming.ts | script | 1.5 KB |
| templates/hitl-agent.ts | script | 6.6 KB |
| templates/mcp-server-basic.ts | script | 4.0 KB |
| templates/rag-agent.ts | script | 4.8 KB |
| templates/react-useagent-client.tsx | other | 5.5 KB |
| templates/scheduled-agent.ts | script | 4.5 KB |
| templates/state-sync-agent.ts | script | 3.9 KB |
| templates/websocket-agent.ts | script | 4.1 KB |
| templates/workflow-agent.ts | script | 3.8 KB |
| templates/wrangler-agents-config.jsonc | other | 1.9 KB |
references/configuration-guide.md
View on GitHub## Configuration Deep Dive
### Complete wrangler.jsonc Example
```jsonc
{
"$schema": "node_modules/wrangler/config-schema.json",
"name": "my-agent",
"main": "src/index.ts",
"account_id": "YOUR_ACCOUNT_ID",
"compatibility_date": "2025-10-21",
"compatibility_flags": ["nodejs_compat"],
// Durable Objects configuration (REQUIRED)
"durable_objects": {
"bindings": [
{
"name": "MyAgent",
"class_name": "MyAgent"
}
]
},
// Migrations (REQUIRED)
"migrations": [
{
"tag": "v1",
"new_sqlite_classes": ["MyAgent"] // Enables state persistence
}
],
// Optional: Workers AI binding (for AI model calls)
"ai": {
"binding": "AI"
},
// Optional: Vectorize binding (for RAG)
"vectorize": {
"bindings": [
{
"binding": "VECTORIZE",
"index_name": "my-agent-vectors"
}
]
},
// Optional: Browser Rendering binding (for web browsing)
"browser": {
"binding": "BROWSER"
},
// Optional: Workflows binding (for async workflows)
"workflows": [
{
"name": "MY_WORKFLOW",
"class_name": "MyWorkflow",
"script_name": "my-workflow-script" // If in different project
}
],
// Optional: D1 binding (for additional persistent data)
"d1_databases": [
{
"binding": "DB",
"database_name": "my-agent-db",
"database_id": "your-database-id"
}
],
// Optional: R2 binding (for file storage)
"r2_buckets": [
{
"binding": "BUCKET",
"bucket_name": "my-agent-files"
}
],
// Optional: Environment variables
"vars": {
"ENVIRONMENT": "production"
},
// Optional: Secrets (set with: wrangler secret put KEY)
// OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.
// Observability
"observability": {
"enabled": true
}
}
```
### Migrations Best Practices
**Atomic Deployments**: Migrations are **atomic operations** - they cannot be gradually deployed.
```jsonc
{
"migrations": [
{
"tag": "v1",
"new_sqlite_classes": ["MyAgent"] // Initial: enable SQLite
},
{
"tag": "v2",
"renamed_classes": [
{"from": "MyAgent", "to": "MyRenamedAgent"}
]
},
{
"tag": "v3",
"deleted_classes": ["OldAgent"]
},
{
"tag": "v4",
"transferred_classes": [
{
"from": "AgentInOldScript",
"from_script": "old-worker",
"to": "AgentInNewScript"
}
]
}
]
}
```
**Migration Rules:**
- ✅ Each migration needs a unique `tag`
- ✅ Cannot enable SQLite on existing deployed class (must be in first migration)
- ✅ Migrations apply in order during deployment
- ✅ Cannot edit or remove previous migration tags
- ❌ Never deploy new migrations gradually (atomic only)
### Environment-Specific Migrations
```jsonc
{
"migrations": [{"tag": "v1", "new_sqlite_classes": ["MyAgent"]}],
"env": {
"staging": {
"migrations": [
{"tag": "v1", "new_sqlite_classes": ["MyAgent"]},
{"tag": "v2-staging", "renamed_classes": [{"from": "MyAgent", "to": "StagingAgent"}]}
]
}
}
}
```
---
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |