Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/smicolon/ai-kitnpx agentmods add commands/smicolon/ai-kit/project-initWrote 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/smicolon/ai-kit/project-init)<a href="https://agentmods.dev/commands/smicolon/ai-kit/project-init"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/project-init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/smicolon/ai-kit/project-init"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/project-init.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00015 | $0.01708 |
| Opus 5 | $0.00008 | $0.00854 |
| Sonnet 5 | $0.00003 | $0.00342 |
| Haiku 4.5 | $0.00002 | $0.00171 |
Grade A, and why
project-init 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 6d 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.
curl http://localhost:3000/health How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Hono Project
Create a new Hono project with proper structure and configuration.
Workflow
Step 1: Choose Template
Ask the user which template to use:
-
Bun + Cloudflare Workers (Recommended)
- Development with Bun's hot reload
- Deployment to Cloudflare Workers
- D1 database, KV, R2 support
-
Bun Standalone
- Pure Bun runtime
- Local development and deployment
- Bun SQLite for database
-
Cloudflare Workers Only
- Wrangler for dev and deploy
- Full CF ecosystem
Step 2: Create Project
Template: Bun + Cloudflare Workers
# Create project directory
mkdir {project-name} && cd {project-name}
# Initialize with Bun
bun init -y
# Install dependencies
bun add hono @hono/zod-validator zod
bun add -d @cloudflare/workers-types wrangler typescript
package.json:
{
"name": "{project-name}",
"scripts": {
"dev": "bun run --hot src/index.ts",
"dev:cf": "wrangler dev src/index.ts",
"deploy": "wrangler deploy",
"test": "bun test",
"typecheck": "tsc --noEmit"
},
"dependencies": {
"hono": "^4.0.0",
"@hono/zod-validator": "^0.4.0",
"zod": "^3.23.0"
},
"devDependencies": {
"@cloudflare/workers-types": "^4.0.0",
"typescript": "^5.0.0",
"wrangler": "^3.0.0"
}
}
tsconfig.json:
{
"compilerOptions": {
"target": "ESNext",
"module": "ESNext",
"moduleResolution": "bundler",
"strict": true,
"skipLibCheck": true,
"lib": ["ESNext"],
"types": ["@cloudflare/workers-types", "bun-types"],
"jsx": "react-jsx",
"jsxImportSource": "hono/jsx",
"baseUrl": ".",
"paths": {
"@/*": ["src/*"]
}
},
"include": ["src/**/*", "tests/**/*"],
"exclude": ["node_modules"]
}
wrangler.toml:
name = "{project-name}"
main = "src/index.ts"
compatibility_date = "2024-01-01"
[vars]
ENVIRONMENT = "production"
# Uncomment to enable D1
# [[d1_databases]]
# binding = "DB"
# database_name = "{project-name}-db"
# database_id = "your-database-id"
# Uncomment to enable KV
# [[kv_namespaces]]
# binding = "KV"
# id = "your-kv-id"
# Uncomment to enable R2
# [[r2_buckets]]
# binding = "BUCKET"
# bucket_name = "{project-name}-bucket"
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.
- 6d ago First seen · 307 lines · 15 tokens per session scan A fce0d8ed4895
project-init is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 1,708 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
migrate-architecture
Plan and execute major architecture migrations with zero downtime, including monolith-to-microservices, database migrations, cloud migrations, and technology stack changes.
scaffold-python-worker
Scaffold a standalone Python 3.14 background worker service. Use for event-driven or scheduled processing jobs that are NOT FastAPI REST APIs and NOT AI agents.
diagnose-sse
Command: /diagnose-sse Agent: sse Skill: sse-scanner.
saas
One-line SaaS — from a description, scaffold a complete CF-native multi-tenant SaaS (Hono + D1 + Drizzle + Better Auth + Stripe + shadcn) deployed to a real URL.
apim-setup
Execute the apim setup workflow with deterministic validation and redacted output.
add-api-azure
Create a new Azure Function HTTP endpoint with full integration.