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/savagelysubtle/big-brain-memory-bank/520-xml-structuregit 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/520-xml-structure)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/520-xml-structure"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/520-xml-structure.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 | $0.00000 | $0.01455 |
| Opus 5 | $0.00000 | $0.00727 |
| Sonnet 5 | $0.00000 | $0.00291 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
520-xml-structure 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 5d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN creating or editing Cursor Rule (.mdc) files ENSURE using proper XML structure for clarity and AI parsing globs: ["**/*.mdc"] alwaysApply: false
TL;DR: Provides guidance on using XML structure in Cursor Rules to improve clarity and help AI parse instructions effectively.
1.0.0
<structure-element>
<tag>context</tag>
<purpose>Explains when and why the rule applies</purpose>
<example><![CDATA[<context>
This rule applies when working with React components. ]]>
<structure-element>
<tag>requirements</tag>
<purpose>Lists what must be followed when the rule is active</purpose>
<example><![CDATA[<requirements>
Use functional components instead of class components Implement proper prop type validation Follow React hooks best practices ]]>
<structure-element>
<tag>examples</tag>
<purpose>Provides implementation examples</purpose>
<example><![CDATA[<examples>
<structure-element>
<tag>details</tag>
<purpose>Contains detailed sections with specific information</purpose>
<example><![CDATA[<details>
SECTION TITLE Detailed information about this section
<principle>
<n>Place Critical Content First</n>
<description>Organize sections in descending order of importance</description>
<steps>
<step>Essential requirements first</step>
<step>Implementation details next</step>
<step>Examples and edge cases last</step>
</steps>
</principle>
<principle>
<n>Progressive Disclosure</n>
<description>Reveal information based on complexity and importance</description>
<steps>
<step>Start with the most essential instructions</step>
<step>Add details in subsequent sections</step>
<step>Place edge cases and rare scenarios at the end</step>
</steps>
</principle>
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.
- 5d ago First seen · 199 lines · 0 tokens per session scan A 13a0ddabf8e6
520-xml-structure 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 1,455 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-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
composer-core
Always-on builder spine — continue the app, demoable slice, Build loop, Run/Wired handoff, ask only on high confusion weight.
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-deep-research
Edge-case research for audits, vendor comparisons, and unfamiliar APIs — primaries first, iterative retrieval, explicit conflicts; not the default build path.