The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.
日本語の概要は準備中です。原文の説明を表示しています。
Deploy and manage Cloudflare Workers, Pages, R2, D1, KV. Use when working with wrangler, Cloudflare Workers, or edge deployments.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Version: 4.59.2+ (Jan 2026). Config format:
wrangler.jsoncrecommended over.toml.
# Create new project
npx create-cloudflare@latest my-worker
# Local dev
wrangler dev
# Deploy
wrangler deploy
# View logs
wrangler tail
Deploy Worker to Cloudflare:
1. Check wrangler.jsonc exists with name, main, compatibility_date
2. wrangler deploy (auto-provisions KV/R2/D1 bindings if IDs missing)
3. wrangler tail to verify
| Task | Command |
|---|---|
| Local dev | wrangler dev |
| Deploy | wrangler deploy |
| View logs | wrangler tail |
| Add secret | wrangler secret put NAME |
| List secrets | wrangler secret list |
| Generate types | wrangler types |
| Check config | wrangler check startup |
{
"name": "my-worker",
"main": "src/index.ts",
"compatibility_date": "2025-01-01",
// Routes
"routes": [
{ "pattern": "example.com/*", "zone_name": "example.com" }
],
// Bindings (IDs optional - auto-provisioned on deploy)
"kv_namespaces": [{ "binding": "KV", "id": "..." }],
"r2_buckets": [{ "binding": "BUCKET", "bucket_name": "my-bucket" }],
"d1_databases": [{ "binding": "DB", "database_id": "..." }],
// Environment variables
"vars": { "ENV": "production" }
}
Add bindings WITHOUT IDs — Wrangler creates resources on deploy:
{
"kv_namespaces": [{ "binding": "CACHE" }], // No id - auto-created
"r2_buckets": [{ "binding": "ASSETS" }], // No bucket_name - auto-created
"d1_databases": [{ "binding": "DB" }] // No database_id - auto-created
}
| Flag | Purpose |
|---|---|
--x-provision | Force auto-provision resources |
--x-auto-create | Auto-create bindings with new resources |
--x-autoconfig | Auto-detect framework (Next.js, Remix, etc.) |
| Variable | Purpose |
|---|---|
CLOUDFLARE_API_TOKEN | Auth for CI/CD |
CLOUDFLARE_ACCOUNT_ID | Override account |
What to do?
├─ New project → npx create-cloudflare@latest
├─ Local dev → wrangler dev
├─ Deploy → wrangler deploy
├─ Add secret → wrangler secret put NAME
├─ View logs → wrangler tail
├─ Database ops → wrangler d1 ...
├─ Storage ops → wrangler r2 ... or wrangler kv ...
└─ Scheduled jobs → Add [triggers] to config
wrangler secret put API_KEY
# Enter value when prompted (or pipe: echo "value" | wrangler secret put API_KEY)
{
"name": "my-worker",
"env": {
"staging": {
"vars": { "ENV": "staging" },
"routes": [{ "pattern": "staging.example.com/*" }]
},
"production": {
"vars": { "ENV": "production" },
"routes": [{ "pattern": "example.com/*" }]
}
}
}
wrangler deploy --env staging
wrangler deploy --env production
wrangler d1 create my-db
wrangler d1 execute my-db --file schema.sql
wrangler d1 execute my-db --command "SELECT * FROM users"
wrangler r2 bucket create my-bucket
wrangler r2 object put my-bucket/file.txt --file ./local.txt
wrangler r2 object get my-bucket/file.txt
Copy this to your project's AGENTS.md:
### Cloudflare Wrangler
Wrangler is installed and authenticated.
R2 bucket: `<BUCKET_NAME>`
Account ID: `<ACCOUNT_ID>`
Common commands:
\`\`\`bash
wrangler r2 object put <BUCKET>/<path> --file ./local-file
wrangler r2 object get <BUCKET>/<path> --file ./downloaded
wrangler r2 bucket list
wrangler d1 execute <DB> --command "SELECT * FROM users"
wrangler deploy
\`\`\`
| Topic | Reference |
|---|---|
| All commands | COMMANDS.md |
| Config options | CONFIG.md |
| Pages deployment | PAGES.md |
"keep_vars": true to preserve dashboard editswrangler secret put, never put secrets in configwrangler types after config changesまだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.
日本語の概要は準備中です。原文の説明を表示しています。
MCP Agent Mail for multi-agent coordination. Use when agents need file locks, messaging, inboxes, or conflict prevention. Handles macro_start_session, file_reservation_paths, send_message, threading, pre-commit guards.
日本語の概要は準備中です。原文の説明を表示しています。
Jeffrey Emanuel's multi-agent implementation workflow using NTM, Agent Mail, Beads, and BV. The execution phase that follows planning and bead creation. Includes exact prompts used.
日本語の概要は準備中です。原文の説明を表示しています。
Convert markdown plans into beads with dependencies using br CLI. Use when creating task graphs, polishing beads before implementation, or bridging planning to agent swarm execution.
日本語の概要は準備中です。原文の説明を表示しています。
Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.
日本語の概要は準備中です。原文の説明を表示しています。
Manage AI coding CLI accounts with sub-100ms switching. Use when hitting rate limits on Claude Max, GPT Pro, or Gemini Ultra subscriptions and need instant account swapping without browser OAuth.
日本語の概要は準備中です。原文の説明を表示しています。