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.
git clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-BankWrote 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/savagelysubtle/big-brain-memory-bank/530-glob-patterns)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/530-glob-patterns"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/530-glob-patterns.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01623 |
| Opus 5 | $0.00000 | $0.00812 |
| Sonnet 5 | $0.00000 | $0.00325 |
| Haiku 4.5 | $0.00000 | $0.00162 |
Grade A, and why
530-glob-patterns 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 8d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN defining glob patterns in Cursor Rule (.mdc) files ENSURE using precise and optimized patterns globs: ["**/*.mdc"] alwaysApply: false
TL;DR: Provides guidance for crafting efficient, precise glob patterns in Cursor Rules to target specific files while avoiding performance issues.
1.0.0
<pattern-type>
<n>Extension-Based Targeting</n>
<example>"*.{ts,tsx}"</example>
<description>Targets specific file types regardless of location</description>
</pattern-type>
<pattern-type>
<n>Specific File Targeting</n>
<example>"src/config/settings.js"</example>
<description>Targets individual files</description>
</pattern-type>
<pattern-type>
<n>Multiple Pattern Arrays</n>
<example>
globs:
- "src/**/*.ts"
- "src/**/*.tsx"
- "lib/**/*.js"
</example>
<description>Targets multiple file patterns</description>
</pattern-type>
<best-practice>
<n>Use Explicit Paths</n>
<description>Target specific directories rather than searching everywhere</description>
<comparison>
<bad>"**/*.ts" (Inefficient)</bad>
<good>"src/**/*.ts", "lib/**/*.ts" (Efficient)</good>
</comparison>
</best-practice>
<best-practice>
<n>Minimize Nesting Depth</n>
<description>Patterns with multiple "**/'" are slower to evaluate</description>
<comparison>
<bad>"src/**/**/**/*.js" (Inefficient)</bad>
<good>"src/**/*.js" (Efficient)</good>
</comparison>
</best-practice>
<table>
<heading>Performance Benchmarks for Large Projects</heading>
<row>
<cell>Approach</cell>
<cell>100k Files</cell>
<cell>1M Files</cell>
</row>
<row>
<cell>Broad "**/*"</cell>
<cell>2.1s</cell>
<cell>24.8s</cell>
</row>
<row>
<cell>Targeted Globs</cell>
<cell>0.3s</cell>
<cell>1.9s</cell>
</row>
<row>
<cell>Globs + Exclusions</cell>
<cell>0.2s</cell>
<cell>1.2s</cell>
</row>
</table>
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.
- 8d ago First seen · 213 lines · 0 tokens per session scan A 50d04ab6b371
530-glob-patterns is a cursor rule published in the GitHub repository savagelysubtle/BIG-BRAIN-Memory-Bank (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,623 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 2026-08-31.
Other cursor rules, from other repositories
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-reasoning
High-stakes judgment for architectural or multi-option work — tradeoffs, one-way doors, reason-then-re-evaluate, honest pushback.
clarify-first
Infer-and-act by default — ask only on high confusion weight, after inspecting, with a decision-linked question.
composer-debugging
Root-cause debugging — reproduce, trace data flow, test cheapest hypothesis, fix the cause not the symptom.
composer-fullstack-delivery
New screen, feature, endpoint, or multi-layer slice — freeze seams, ship one demoable path, failure modes, Run/Wired handoff.