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/route-createWrote 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/route-create)<a href="https://agentmods.dev/commands/smicolon/ai-kit/route-create"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/route-create/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/route-create"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/route-create.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 | $0.00016 | $0.00965 |
| Opus 5 | $0.00008 | $0.00483 |
| Sonnet 5 | $0.00003 | $0.00193 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
route-create scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Hono Route
Create a new Hono route following project conventions.
Workflow
Step 1: Gather Requirements
Ask the user:
- Resource name (e.g., "users", "posts", "orders")
- Operations needed (GET list, GET single, POST, PUT, DELETE)
- Fields/schema for the resource
- Relationships to other resources
- Authentication requirements
Step 2: Create Zod Schema
Create validator file first:
// validators/{resource}.schema.ts
import { z } from 'zod'
export const create{Resource}Schema = z.object({
// Fields based on user requirements
})
export const update{Resource}Schema = create{Resource}Schema.partial()
export const {resource}ParamsSchema = z.object({
id: z.string().uuid(),
})
export const {resource}QuerySchema = z.object({
page: z.coerce.number().int().positive().default(1),
limit: z.coerce.number().int().min(1).max(100).default(20),
})
// Export types
export type Create{Resource} = z.infer<typeof create{Resource}Schema>
export type Update{Resource} = z.infer<typeof update{Resource}Schema>
Step 3: Create Route File
// routes/{resource}.ts
import { Hono } from 'hono'
import { zValidator } from '@hono/zod-validator'
import type { Env } from '../types/bindings'
import {
create{Resource}Schema,
update{Resource}Schema,
{resource}ParamsSchema,
{resource}QuerySchema
} from '../validators/{resource}.schema'
const {resource} = new Hono<Env>()
// GET /{resource} - List
{resource}.get('/',
zValidator('query', {resource}QuerySchema),
async (c) => {
const { page, limit } = c.req.valid('query')
// Implementation
return c.json({ data: [], meta: { page, limit } })
}
)
// GET /{resource}/:id - Get single
{resource}.get('/:id',
zValidator('param', {resource}ParamsSchema),
async (c) => {
const { id } = c.req.valid('param')
// Implementation
return c.json({ id })
}
)
// POST /{resource} - Create
{resource}.post('/',
zValidator('json', create{Resource}Schema),
async (c) => {
const data = c.req.valid('json')
// Implementation
return c.json({ id: crypto.randomUUID(), ...data }, 201)
}
)
// PUT /{resource}/:id - Update
{resource}.put('/:id',
zValidator('param', {resource}ParamsSchema),
zValidator('json', update{Resource}Schema),
async (c) => {
const { id } = c.req.valid('param')
const data = c.req.valid('json')
// Implementation
return c.json({ id, ...data })
}
)
// DELETE /{resource}/:id - Delete
{resource}.delete('/:id',
zValidator('param', {resource}ParamsSchema),
async (c) => {
const { id } = c.req.valid('param')
// Implementation
return c.body(null, 204)
}
)
export { {resource} }
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 · 154 lines · 16 tokens per session scan A 56fd288fc65d
route-create is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 965 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
ctx:design
Design system architecture, APIs, and component interfaces with structured workflow.
flow-nexus-workflow
Event-driven workflow automation with message queues.
architect
System design with Memory-based coordination for scalable architectures.
coder
Autonomous code generation with batch file operations.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.