000-xml-cursor-rules

000-xml-cursor-rules is a cursor rule for Cursor from savagelysubtle/BIG-BRAIN-Memory-Bank. It costs 0 tokens per session (2,060 once invoked), scanned A, original, MIT.

A naming and formatting rule for Cursor Rule files, which are Markdown files that guide an AI coding assistant. It defines prefixes and file-matching patterns for areas such as core standards, languages, testing, documentation, and configuration.

In plain words
What is it for?
Use it when creating or updating `.mdc` rules and deciding their names, XML structure, and file patterns.
Why use it?
It makes rules easier to classify and ensures the right rules can be associated with the relevant files.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions Cursor.

Install

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.

agentmods
npx agentmods add rules/savagelysubtle/big-brain-memory-bank/000-xml-cursor-rules
Clone the repo
git clone --depth 1 https://github.com/savagelysubtle/BIG-BRAIN-Memory-Bank

Made for: Cursor.

Wrote 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.

agentmods badge for 000-xml-cursor-rules

README.md
[![agentmods](https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/000-xml-cursor-rules.svg)](https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/000-xml-cursor-rules)
Your own site
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/000-xml-cursor-rules"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/000-xml-cursor-rules.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 2,060 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.02060
Opus 5 $0.00000 $0.01030
Sonnet 5 $0.00000 $0.00412
Haiku 4.5 $0.00000 $0.00206

Measured 6d ago against content hash fc9e8d4ba9b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

000-xml-cursor-rules 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 6d 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.

inspiration/original-concepts/My-memory-bank/.cursor/rules/000-xml-cursor-rules.mdc · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<naming-convention>
  <pattern>PREFIX-name.mdc</pattern>
  <prefixes>
    <prefix code="0XX">Core standards (highest priority)</prefix>
    <prefix code="1XX">Tool configs</prefix>
    <prefix code="3XX">Testing standards</prefix>
    <prefix code="4XX">Documentation standards</prefix>
    <prefix code="1XXX">Language rules</prefix>
    <prefix code="2XXX">Framework rules</prefix>
    <prefix code="8XX">Workflows</prefix>
    <prefix code="9XX">Templates</prefix>
    <prefix code="__XXX_name.mdc">Private rules</prefix>
  </prefixes>
</naming-convention>

<glob-patterns>
  <pattern type="core-standards">.cursor/rules/*.mdc</pattern>
  <pattern type="language-rules">src/**/*.{js,ts}</pattern>
  <pattern type="testing-standards">**/*.test.{js,ts}</pattern>
  <pattern type="react-components">src/components/**/*.tsx</pattern>
  <pattern type="documentation">docs/**/*.md</pattern>
  <pattern type="configuration">*.config.{js,json}</pattern>
  <pattern type="build-artifacts">dist/**/*</pattern>
  <pattern type="multiple-extensions">src/**/*.{js,jsx,ts,tsx}</pattern>
  <pattern type="multiple-files">dist/**/*, docs/**/*.md</pattern>
</glob-patterns>
<description-field>
  <format>Use deterministic ACTION TRIGGER OUTCOME format</format>
  <pattern>WHEN X occurs THEN do Y (e.g., "WHEN writing Python code ALWAYS use type hints")</pattern>
  <length>Keep under 120 characters while maintaining clear intent</length>
</description-field>

<globs-field>
  <format>Standard glob patterns without quotes</format>
  <examples>
    <example>*.js</example>
    <example>src/**/*.py</example>
    <example>**/*.{ts,tsx}</example>
  </examples>
</globs-field>
<trigger-sections>
  <section name="activation">
    <purpose>Define clear trigger conditions and responses</purpose>
    <example>
      &lt;activation&gt;
        &lt;trigger&gt;Memory bank update&lt;/trigger&gt;
        &lt;action&gt;Review all memory bank files&lt;/action&gt;
      &lt;/activation&gt;
    </example>
  </section>
</trigger-sections>

<procedural-sections>
  <section name="steps" or "process" or "workflow">
    <purpose>Define ordered sequences of actions</purpose>
    <example>
      &lt;process&gt;
        &lt;step&gt;Review requirements&lt;/step&gt;
        &lt;step&gt;Analyze existing code&lt;/step&gt;
        &lt;step&gt;Create implementation plan&lt;/step&gt;
      &lt;/process&gt;
    </example>
  </section>
</procedural-sections>

Read the full file on GitHub · 192 lines

Changes

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.

  1. 6d ago First seen · 192 lines · 0 tokens per session scan A fc9e8d4ba9b2

Subscribe to this mod's changes

000-xml-cursor-rules 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 2,060 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.