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/cloudflare-infrastructureWrote 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/cloudflare-infrastructure)<a href="https://agentmods.dev/rules/brendadeeznuts1111/betting-brain-v3/cloudflare-infrastructure"><img src="https://agentmods.dev/badge/rules/brendadeeznuts1111/betting-brain-v3/cloudflare-infrastructure/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/cloudflare-infrastructure"><img src="https://agentmods.dev/badge/rules/brendadeeznuts1111/betting-brain-v3/cloudflare-infrastructure.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 | $0.00007 | $0.04089 |
| Opus 5 | $0.00003 | $0.02044 |
| Sonnet 5 | $0.00001 | $0.00818 |
| Haiku 4.5 | $0.00001 | $0.00409 |
Grade A, and why
cloudflare-infrastructure scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
async fetch(request: Request, env: Env): Promise<Response> { How it starts
The opening of the file, as written. The whole thing — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Infrastructure Rules
🔍 Code Searchability Patterns
Find Cloudflare Infrastructure Issues with ast-grep
# Find D1 database bindings
ast-grep --pattern 'env.$DB.prepare($QUERY)' src/
ast-grep --pattern 'env.ANALYTICS.prepare' src/
ast-grep --pattern 'env.RAW_FEED_DB.prepare' src/
sg -p 'env.$DB.prepare' src/
sg -p 'env.ANALYTICS' src/
sg -p 'env.RAW_FEED_DB' src/
# Find KV namespace usage
ast-grep --pattern 'env.$KV.get($KEY)' src/
ast-grep --pattern 'env.$KV.put($KEY, $VALUE)' src/
sg -p 'env.$KV.get' src/
sg -p 'env.$KV.put' src/
# Find queue operations
ast-grep --pattern 'env.$QUEUE.send($MESSAGE)' src/
ast-grep --pattern 'env.LINE_INGRESS.send' src/
sg -p 'env.$QUEUE.send' src/
sg -p 'env.LINE_INGRESS' src/
# Find Analytics Engine usage
ast-grep --pattern 'env.ANALYTICS_ENGINE.writeDataPoint' src/
sg -p 'env.ANALYTICS_ENGINE' src/
Cloudflare Infrastructure Discovery Commands
sg search "env.ANALYTICS" src/
sg search "env.RAW_FEED_DB" src/
sg search "env.BET_TICKER_RAW" src/
sg search "env.LINE_INGRESS" src/
sg search "env.ANALYTICS_ENGINE" src/
Search Examples
# Find all D1 database operations
sg search 'env.$DB.prepare' src/
# Find KV operations
sg search 'env.$KV.get' src/
# Find queue operations
sg search 'env.$QUEUE.send' src/
# Find Analytics Engine usage
sg search 'env.ANALYTICS_ENGINE' src/
🏗️ Infrastructure Patterns
D1 Database Operations
Parameterized Queries (CRITICAL)
// ✅ CORRECT: Parameterized query
const result = await env.ANALYTICS.prepare(`
SELECT * FROM line_movements
WHERE eid = ? AND ts > ?
LIMIT ?
`).bind(eventID, timestamp, limit).all();
// ❌ WRONG: String interpolation (SQL injection risk)
const result = await env.ANALYTICS.prepare(`
SELECT * FROM line_movements
WHERE eid = '${eventID}' AND ts > '${timestamp}'
LIMIT ${limit}
`).all();
Type Safety with D1 Results
import { normalizeD1Result } from '../utils/request';
// ✅ CORRECT: Type-safe D1 results
const result = await env.ANALYTICS.prepare(`
SELECT eid, mt, ts, old_line, new_line
FROM line_movements
WHERE eid = ?
ORDER BY ts DESC
LIMIT ?
`).bind(eventID, limit).all();
type Movement = {
eid: string;
mt: string;
ts: string;
old_line: number;
new_line: number;
};
const movements = normalizeD1Result<Movement>(result);
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.
- 10d ago First seen · 590 lines · 7 tokens per session scan A fc1eea00596f
cloudflare-infrastructure is a cursor rule published in the GitHub repository brendadeeznuts1111/betting-brain-v3 (8 stars, last pushed 11mo ago), licensed MIT. It adds 7 tokens to every session and 4,089 once invoked, about $0.0000 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
00-cloud-agent-mandatory
Necessary for cloud agents.
workflow-deployment
Workflow testing and deployment process guide.
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.
consumer-meta
A per-project metadata file and registry for recording runtime facts such as development ports, authentication, databases, deployment platforms, and verification details.
dev-port-allocation
A shared process for assigning development-server ports to different projects and checking that their declarations match the central registry.
dev-tunnel-convention
An index of shared conventions for development tunnels made with Cloudflare tools. A development tunnel exposes a local server through a network address so it can be reviewed remotely.