510-memory-diagnostics

510-memory-diagnostics is a cursor rule for Cursor from savagelysubtle/BIG-BRAIN-Memory-Bank. It costs 0 tokens per session (1,087 once invoked), scanned A, original, MIT.

A set of rules for checking the health of a Memory Bank, a folder of project notes that stores context such as requirements, technical details, current work, and progress.

In plain words
What is it for?
Use it when the command includes “MEMORY HEALTH CHECK” or “CHECK MEMORY BANK” to inspect required files, information consistency, and the expected memory directories.
Why use it?
It helps detect missing files, contradictory notes, broken links between levels of project context, and an incorrect folder structure.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when the command includes “MEMORY HEALTH CHECK” or “CHECK MEMORY BANK” to inspect required files, information consistency, and the expected memory directories.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/savagelysubtle/big-brain-memory-bank/510-memory-diagnostics
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.

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 510-memory-diagnostics

README.md
[![agentmods](https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/510-memory-diagnostics/github.svg)](https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/510-memory-diagnostics)
Your own site
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/510-memory-diagnostics"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/510-memory-diagnostics/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 510-memory-diagnostics

Your own site · 80×15
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/510-memory-diagnostics"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/510-memory-diagnostics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,087 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01087
Opus 5 $0.00000 $0.00544
Sonnet 5 $0.00000 $0.00217
Haiku 4.5 $0.00000 $0.00109

Measured 8d ago against content hash e3382baaa79b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

510-memory-diagnostics 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.

.cursor/rules/BIG_BRAIN/Utilities/510-memory-diagnostics.mdc · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: WHEN command includes "MEMORY HEALTH CHECK" or "CHECK MEMORY BANK" ENSURE performing thorough memory system diagnostics globs: ["/memory-bank/", "/*.md", "/*.mdc"] alwaysApply: true

TL;DR: Provides comprehensive diagnostics for checking Memory Bank integrity, consistency, and health.

1.0.0

Critical Files:

  • [✓/✗] projectbrief.md - Exists and valid
  • [✓/✗] productContext.md - Exists and valid
  • [✓/✗] activeContext.md - Exists and valid
  • [✓/✗] systemPatterns.md - Exists and valid
  • [✓/✗] techContext.md - Exists and valid
  • [✓/✗] progress.md - Exists and valid
  • [✓/✗] tasks.md - Exists and valid
  • [✓/✗] projectRules.md - Exists and valid

Memory Hierarchy:

  • [✓/✗] Consistent information flow from foundation to tracking layers
  • [✓/✗] No critical contradictions between files
  • [✓/✗] Proper layer relationships maintained

Directory Structure:

  • [✓/✗] memory-bank/active/ directory present
  • [✓/✗] memory-bank/short-term/ directory present
  • [✓/✗] memory-bank/long-term/ directories present
    </template>
  </content>
</details>

<details>
  <section-name>CONSISTENCY CHECKING</section-name>
  <content>
    <check-category>
      <name>Workflow Mode Consistency</name>
      <checks>
        <check>Check if workflow mode is consistently specified across files</check>
        <check>Verify that activeContext.md clearly states current mode</check>
      </checks>
    </check-category>
    <check-category>
      <name>Task Status Consistency</name>
      <checks>
        <check>Ensure task status is consistent between active context and progress</check>
        <check>Verify completed items are properly marked in all relevant files</check>
      </checks>
    </check-category>
    <check-category>
      <name>Project Direction Alignment</name>
      <checks>
        <check>Check that current tasks align with project brief objectives</check>
        <check>Verify that progress aligns with overall product goals</check>
      </checks>
    </check-category>
    <check-category>
      <name>Technical Implementation Consistency</name>
      <checks>
        <check>Verify system patterns and implementation match tech context</check>
        <check>Check for contradictions in technical approaches</check>
      </checks>
    </check-category>
  </content>
</details>

<details>
  <section-name>DIAGNOSTIC REPORT</section-name>
  <content>
    <report-element>Overall memory system status (Healthy/Warning/Critical)</report-element>
    <report-element>List of specific issues found (if any)</report-element>
    <report-element>Recommendations for resolving issues</report-element>
    <report-element>Suggestions for memory system improvements</report-element>
  </content>
</details>

<details>
  <section-name>RECOVERY RECOMMENDATIONS</section-name>
  <content>
    <recommendation-element>Clear explanation of the issue and its impact</recommendation-element>
    <recommendation-element>Step-by-step recovery procedure</recommendation-element>
    <recommendation-element>Prevention strategies to avoid future occurrences</recommendation-element>
  </content>
</details>

Read the full file on GitHub · 134 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. 8d ago First seen · 134 lines · 0 tokens per session scan A e3382baaa79b

Subscribe to this mod's changes

510-memory-diagnostics 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 1,087 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.