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/quality-standardsWrote 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/quality-standards)<a href="https://agentmods.dev/rules/brendadeeznuts1111/betting-brain-v3/quality-standards"><img src="https://agentmods.dev/badge/rules/brendadeeznuts1111/betting-brain-v3/quality-standards/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/quality-standards"><img src="https://agentmods.dev/badge/rules/brendadeeznuts1111/betting-brain-v3/quality-standards.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 | $0.03094 | $0.03094 |
| Opus 5 | $0.01547 | $0.01547 |
| Sonnet 5 | $0.00619 | $0.00619 |
| Haiku 4.5 | $0.00309 | $0.00309 |
Grade A, and why
quality-standards scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Standards Rules
🎯 Overview
These rules enforce the quality standards defined in docs/QUALITY_STANDARDS.md.
Zero Tolerance:
- ❌ No
as anytype assertions - ❌ No
console.log/error(use StructuredLogger) - ❌ No magic numbers (use constants)
- ❌ No code duplication (use utilities)
- ❌ No empty catch blocks
🔍 Code Searchability Patterns
Find Quality Issues with ast-grep
# Find 'as any' type assertions (CRITICAL)
ast-grep --pattern 'as any' src/
sg -p 'as any' src/
# Find console.log usage (should use StructuredLogger)
ast-grep --pattern 'console.$METHOD($$$)' src/
sg -p 'console.log' src/
sg -p 'console.error' src/
# Find magic numbers (should use constants)
ast-grep --pattern '$NUM' src/
sg -p '90' src/ # Example: find hardcoded 90
sg -p '5000' src/ # Example: find hardcoded 5000
# Find empty catch blocks
ast-grep --pattern 'catch ($VAR) { }' src/
sg -p 'catch' src/
# Find duplicate code patterns
ast-grep --pattern 'const $VAR = Date.now().toString(36)' src/
sg -p 'Date.now().toString' src/
Quality Enforcement Commands
# Run all quality checks
sg scan --filter "detect-type-assertion-any"
sg scan --filter "detect-console-in-source"
sg scan --filter "detect-magic-numbers"
# Find specific anti-patterns
sg search 'as any' src/
sg search 'console.log' src/
sg search 'Date.now().toString' src/
1. Type Safety - No 'as any'
❌ WRONG
const result = (await query.all()) as any;
const data = result.results || [];
const metrics = { ...testData } as any;
✅ CORRECT
// Use type guards
function isQueryResult(val: unknown): val is QueryResult {
return typeof val === 'object' && val !== null && 'results' in val;
}
const result = await query.all();
const data = isQueryResult(result) ? result.results : [];
// Use utilities
import { normalizeD1Result } from '../utils/request';
const data = normalizeD1Result<MyType>(await query.all());
// Proper type definition
const metrics: CostCapMetrics = {
requests: { current: 0, limit: TEST_LIMITS.REQUESTS, percentage: 0 },
// ... all fields typed
};
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 · 503 lines · 3,094 tokens per session scan A c53a0cc40aed
quality-standards is a cursor rule published in the GitHub repository brendadeeznuts1111/betting-brain-v3 (8 stars, last pushed 11mo ago), licensed MIT. It adds 3,094 tokens to every session, about $0.0155 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 2026-08-31.
Other cursor rules, from other repositories
commit.detail
A detailed checklist for making Git commits safely. It covers reviews, automated checks, documentation alignment, staged-file handling, and release-related safeguards.
review-gui-surface
A standard procedure for agents and handoff tools that use a review interface with screenshots and annotations to inspect completed work.
proactive-skills.manual-review-entry
A set of rules for entering a human review stage after implementation, including automatic triage of unfinished items and a script that checks whether the work is ready for review.
checker-subagent
A rule for sending a newly started checker agent to review changes that could affect shared code, authentication, database migrations, or multiple consumers.
coupling-cohesion
A code-structure guide based on keeping related behavior together and dependencies flowing in clear directions. It covers import cycles, oversized shared files, server boundaries, and repeated decision logic.
agent-self-verification.screenshot-evidence
A procedure for collecting screenshots as proof that a website or interface works as expected. It covers test data, authentication, repeated captures after UI changes, and records of failed verification attempts.