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/brendadeeznuts1111/betting-brain-v3npx agentmods add rules/brendadeeznuts1111/betting-brain-v3/endpoint-routingWrote 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/brendadeeznuts1111/betting-brain-v3/endpoint-routing)<a href="https://agentmods.dev/rules/brendadeeznuts1111/betting-brain-v3/endpoint-routing"><img src="https://agentmods.dev/badge/rules/brendadeeznuts1111/betting-brain-v3/endpoint-routing/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/brendadeeznuts1111/betting-brain-v3/endpoint-routing"><img src="https://agentmods.dev/badge/rules/brendadeeznuts1111/betting-brain-v3/endpoint-routing.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 | $0.03581 | $0.03581 |
| Opus 5 | $0.01791 | $0.01791 |
| Sonnet 5 | $0.00716 | $0.00716 |
| Haiku 4.5 | $0.00358 | $0.00358 |
Grade A, and why
endpoint-routing 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 11d 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:8787/health How it starts
The opening of the file, as written. The whole thing — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Endpoint Routing Rules
🔍 Code Searchability Patterns
Find api-patterns Issues with ast-grep
# Find async function $NAME(request: Request, env: Env, requestId: string)
# Find return createJSONResponse($$$)
# Find return createErrorResponse($$$)
# Find generateRequestId()
# Find createLogger($$$)
ast-grep --pattern 'async function $NAME(request: Request, env: Env, requestId: string)' src/
ast-grep --pattern 'return createJSONResponse($$$)' src/
ast-grep --pattern 'return createErrorResponse($$$)' src/
ast-grep --pattern 'generateRequestId()' src/
ast-grep --pattern 'createLogger($$$)' src/
sg -p 'async' src/
sg -p 'return' src/
sg -p 'return' src/
sg -p 'generateRequestId()' src/
sg -p 'createLogger($$$)' src/
api-patterns Discovery Commands
sg search "async function" src/api/
sg search "createJSONResponse" src/
sg search "generateRequestId" src/
sg search "createLogger" src/
Search Examples
# Find all API endpoint handlers
sg search 'async' src/
# Find JSON response patterns
sg search 'return' src/
# Find request ID generation
sg search 'return' src/
# Find logging patterns
sg search 'generateRequestId()' src/
Main Entry Point
All HTTP requests are handled in src/index.ts via the fetch() handler.
Request Flow Pattern
import { generateRequestId, createOPTIONSResponse, createJSONResponse } from '../utils/request';
import { createLogger } from '../utils/logger';
1. Generate requestId: generateRequestId()
2. Parse URL: new URL(request.url)
3. Log request details with StructuredLogger
4. Handle CORS preflight: createOPTIONSResponse()
5. Route by pathname
6. Return response: createJSONResponse() (includes CORS)
Endpoint Categories
Core System Endpoints (4)
Pattern: Exact pathname match
if (url.pathname === '/health') {
// Health check - used by all dashboards
// Returns: { status, version, timestamp, requestId, duration }
}
if (url.pathname === '/logs') {
// Centralized logging - used by browser extension
// POST: Receives log batches from extension
}
if (url.pathname === '/diagnostics') {
// System diagnostics - used by setup wizard, health monitor
// Returns: bindings status, KV status, last checks
}
if (url.pathname === '/system-status') {
// Detailed status - used by dashboard stats
// Returns: uptime, memory, KV records, health indicators
}
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.
- 11d ago First seen · 596 lines · 3,581 tokens per session scan A aea7f5fc9317
endpoint-routing is a cursor rule published in the GitHub repository brendadeeznuts1111/betting-brain-v3 (8 stars, last pushed 11mo ago), licensed MIT. It adds 3,581 tokens to every session, about $0.0179 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 2026-08-31.
Other cursor rules, from other repositories
workers-patterns
Skim this on every task that touches workers, env, routes, or bindings.
realtime-websockets
Socka-first Durable Object WebSockets, SSR-safe client URLs, no fake localhost. Use for durable-objects/, apps/web, WebSocket forwarding, or @firtoz/socka.
cloudflare-workers
A deployment and configuration guide for Cloudflare Workers, a platform for running server-side code at Cloudflare's edge. It covers NuxtHub, database choices, Wrangler settings, and two deployment paths.
manual-review.backend
The obligations, predicates, evidence schema, failure handling, and review timing in this source are shared. Concrete browser, dispatch, question, filesystem, and command mechanics are target-native and MUST come from the selected runtime fragment at the matching adapter path. A fragment declares only the capability…
api-patterns
MUST define request/response contracts in shared/schemas/ and derive exported types from the same module MUST use Zod validation for all API inputs — getValidatedQuery(event, schema.parse) / readValidatedBody(event, schema.parse) MUST call requireAuth() or requireRole() before any business logic MUST use…
nuxt-security
A shared security baseline for Nuxt applications that use the nuxt-security module. It standardizes browser security headers, content rules, and related settings while allowing documented app-specific exceptions.