Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/movahedan/monobun/securitygit clone --depth 1 https://github.com/movahedan/monobunWhat 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 | $0.00000 | $0.02154 |
| Opus 5 | $0.00000 | $0.01077 |
| Sonnet 5 | $0.00000 | $0.00431 |
| Haiku 4.5 | $0.00000 | $0.00215 |
Grade A, and why
security 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 2d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security
ReDoS Prevention
// ❌ VULNERABLE - Catastrophic backtracking
/.*#(\d+).*/ // Exponential runtime
/^(\w+)(?:\(([^)]+)\))?(!)?:\s*([^\r\n]+?)\s*$/ // Multiple backtracking issues
/.*\d+.*/ // Greedy quantifiers with overlapping patterns
/(a+)+/ // Nested quantifiers (evil regex)
/(a|aa)*/ // Exponential backtracking
/.*#\d+.*/ // Can match anywhere, causes backtracking
// ✅ SECURE - Linear runtime guaranteed
/#(\d+)/ // Direct match, no backtracking
/\d+/ // Simple, direct match
/a+/ // Single quantifier
/(?:a|aa)*/ // Non-capturing, optimized
/\d{1,10}/ // Bounded range
/^#\d+$/ // Anchored to start/end
// ❌ VULNERABLE - alternation with repeated quantifiers (super-linear backtracking)
/^-+|-+$/g // trim hyphens — use a linear scan instead
// ✅ SECURE - trim leading/trailing separators without regex
function trimEdgeHyphens(value: string): string {
let start = 0;
let end = value.length;
while (start < end && value[start] === "-") start++;
while (end > start && value[end - 1] === "-") end--;
return value.slice(start, end);
}
For user-controlled strings (emails, names, slugs), prefer a single-pass character loop over chained .replace(/…/g) when normalizing or stripping edge characters. Cap input length first (for example email local-part ≤ 64).
User-supplied patterns (CLI, config, API)
new RegExp(userControlledString) and then running .test / .match across many paths or rows is a common ReDoS surface. Before any high-fan-out matching:
- Cap pattern size (character limit) and cap each candidate string length so amplification stays bounded.
- Screen the pattern with a catastrophic-backtracking heuristic (for example the
safe-regexpackage used in repo scripts) and reject unsafe patterns with a clear error. Heuristics can false-positive or false-negative; pair them with length limits and simple patterns when possible. - Prefer linear-time matchers (RE2, or constrained glob-to-regex) when the product allows it.
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.
- 2d ago First seen · 227 lines · 0 tokens per session scan A fb6de35e3ffc
security is a cursor rule published in the GitHub repository movahedan/monobun (18 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,154 tokens. 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 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
coolify-ai-docs
Master reference to all Coolify AI documentation in .ai/ directory.
typescript
Changes to these high-fan-out internals can affect every message, delta, element, or rerun. Keep work in them minimal, and benchmark changes with representative stress-test apps.
python_lib
Tips and guidelines specific to the development of the Streamlit Python library, not applicable to scripts and e2e tests.
specs
This directory contains product and tech specs for Streamlit features.