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/500-rule-debugginggit 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/500-rule-debugging)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/500-rule-debugging"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/500-rule-debugging.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 | $0.00793 |
| Opus 5 | $0.00000 | $0.00396 |
| Sonnet 5 | $0.00000 | $0.00159 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
500-rule-debugging 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.
What it actually says
description: WHEN command includes "SHOW ACTIVE RULES" or "DEBUG RULES" ENSURE displaying visible rule information globs: ["/*.md", "/.mdc", "**/.{js,ts,jsx,tsx,py}"] alwaysApply: true
TL;DR: Provides tools for understanding which rules are active and how they're influencing behavior.
1.0.0
ALWAYS-APPLIED RULES:
- 000-memory-bank-core.mdc (Critical memory system operations)
- 010-workflow-modes.mdc (Plan/Act mode implementation)
- 060-platform-awareness.mdc (OS-specific adaptations)
AUTO-ATTACHED RULES:
- 1000-javascript.mdc (Active for *.js files)
- 2000-react.mdc (Active for *.tsx files)
EXPLICITLY REFERENCED RULES:
- creative-phase-examples.mdc (Referenced for current design task)
</template>
</content>
</details>
<details>
<section-name>RULE TRACING</section-name>
<content>
<step>Rule location and filename</step>
<step>Activation trigger (always-applied, glob match, or explicit reference)</step>
<step>Current application status (active/inactive)</step>
<step>Most relevant sections for current context</step>
<step>Any conflicts with other rules</step>
</content>
</details>
<details>
<section-name>GLOB PATTERN ANALYSIS</section-name>
<content>
<step>Interpret the pattern and explain its matching logic</step>
<step>List example files that would match</step>
<step>Identify potential performance issues</step>
<step>Suggest optimizations if applicable</step>
</content>
</details>
<details>
<section-name>CONFLICT DETECTION</section-name>
<content>
<step>Identify rules with overlapping scopes</step>
<step>Highlight contradictory instructions</step>
<step>Explain the precedence rules being applied</step>
<step>Suggest resolution approaches</step>
</content>
</details>
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 · 101 lines · 0 tokens per session scan A d7ac2fbec9d7
500-rule-debugging 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 793 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-fullstack-delivery
New screen, feature, endpoint, or multi-layer slice — freeze seams, ship one demoable path, failure modes, Run/Wired handoff.