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/felipebarcelospro/igniter-jsnpx agentmods add rules/felipebarcelospro/igniter-js/igniter-client-usageWrote 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/rules/felipebarcelospro/igniter-js/igniter-client-usage)<a href="https://agentmods.dev/rules/felipebarcelospro/igniter-js/igniter-client-usage"><img src="https://agentmods.dev/badge/rules/felipebarcelospro/igniter-js/igniter-client-usage/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/rules/felipebarcelospro/igniter-js/igniter-client-usage"><img src="https://agentmods.dev/badge/rules/felipebarcelospro/igniter-js/igniter-client-usage.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 | $0.05663 | $0.05663 |
| Opus 5.5 | $0.02265 | $0.02265 |
| Sonnet 5.5 | $0.01133 | $0.01133 |
| Haiku 4.5 | $0.00566 | $0.00566 |
Grade A, and why
igniter-client-usage 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 1mo 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 — 954 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Igniter.js Client Usage Guide
This rule provides comprehensive guidance on using the Igniter.js Client, which offers universal type-safe API communication across server and client environments with advanced features like real-time updates, caching, and React hooks integration.
1. Universal Client Architecture
1.1 Environment-Aware Client
The Igniter.js client automatically adapts to different execution environments:
// Generated client file: src/igniter.client.ts
export const api = createIgniterClient<AppRouterType>({
baseURL: process.env.NEXT_PUBLIC_IGNITER_API_URL || 'http://localhost:3000',
basePATH: process.env.NEXT_PUBLIC_IGNITER_API_BASE_PATH || '/api/v1',
router: () => {
if (typeof window === 'undefined') {
// Server-side: Direct router access (zero HTTP overhead)
return require('./igniter.router').AppRouter
}
// Client-side: HTTP-based client with hooks
return require('./igniter.schema').AppRouterSchema
},
})
1.2 Execution Environments
Server-Side Execution (RSC, API Routes, Middleware):
- Direct function calls via
router.caller - Zero HTTP overhead
- Full access to server context
- Synchronous execution model
Client-Side Execution (Browser, Client Components):
- HTTP requests via fetch API
- React hooks for state management
- Built-in caching and revalidation
- Real-time subscriptions via SSE
2. Server-Side Usage Patterns
2.1 React Server Components (RSC)
// app/users/page.tsx
import { api } from '@/igniter.client'
export default async function UsersPage() {
// Direct function call - no HTTP request
const users = await api.users.list.query()
return (
<div>
<h1>Users</h1>
{users.data.map(user => (
<div key={user.id}>{user.name}</div>
))}
</div>
)
}
2.2 API Routes
// app/api/sync/route.ts
import { api } from '@/igniter.client'
export async function POST() {
try {
// Direct server-to-server calls
const users = await api.users.list.query()
const posts = await api.posts.list.query()
// Perform sync logic
return Response.json({ success: true })
} catch (error) {
return Response.json({ error: error.message }, { status: 500 })
}
}
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.
- 1mo ago First seen · 954 lines · 5,663 tokens per session scan A 399e7a4c2c83
igniter-client-usage is a cursor rule published in the GitHub repository felipebarcelospro/igniter-js (241 stars, last pushed 11d ago), licensed Apache-2.0. It adds 5,663 tokens to every session, about $0.0227 per session on Opus 5.5. 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 2026-09-01.
Other cursor rules, from other repositories
design-standards
API design standards, HTTP status codes, error handling, and client usage patterns.
lap
LAP CLI -- search, download, and install API specs for AI agents. Use when user needs an API (Stripe, Plaid, Twilio, etc). Commands: (1) npx -y @lap-platform/lapsh search , (2) npx -y @lap-platform/lapsh get -o .lap, (3) npx -y @lap-platform/lapsh skill-install --target cursor. The .lap file IS the spec -- do NOT…
nestjs-api
Cursor rule "nestjs-api" from WellApp-ai/Well, covering api rules (nestjs), module structure, patterns, controllers and dtos with validation.
git
Never mutate git history, remotes, or GitHub repo state.
css
TSF stylesheet conventions, layout debugging, and minification.
200-api-design
200: RESTful API design principles and patterns.