100-memory-file-verification

100-memory-file-verification is a cursor rule for Cursor from savagelysubtle/BIG-BRAIN-Memory-Bank. It costs 0 tokens per session (2,692 once invoked), scanned A, original, MIT.

Rules for checking project memory files before using them. They verify that the files exist, follow the expected Markdown structure, contain the required content, and agree with related files.

In plain words
What is it for?
Use it whenever an agent reads memory files such as project briefs, plans, or other Markdown and MDC records.
Why use it?
It prevents agents from relying on missing, malformed, outdated, or contradictory project notes.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it whenever an agent reads memory files such as project briefs, plans, or other Markdown and MDC records.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/savagelysubtle/big-brain-memory-bank/100-memory-file-verification
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 100-memory-file-verification

README.md
[![agentmods](https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/100-memory-file-verification.svg)](https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/100-memory-file-verification)
Your own site
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/100-memory-file-verification"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/100-memory-file-verification.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 2,692 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 $0.02692
Opus 5 $0.00000 $0.01346
Sonnet 5 $0.00000 $0.00538
Haiku 4.5 $0.00000 $0.00269

Measured 8d ago against content hash 816eece29114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

100-memory-file-verification 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/Core/Verification/100-memory-file-verification.mdc · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: WHEN accessing memory files ENSURE integrity, existence, and format validation globs: ["/*.md", "/*.mdc"] alwaysApply: true

TL;DR: The Memory File Verification system ensures all memory files exist, have the correct structure, and maintain content integrity for reliable memory access.

1.0.0

1. **Existence Verification**
   - Confirms that required files exist in the expected locations
   - Verifies directory structure integrity
   - Checks for missing critical files

2. **Structure Verification**
   - Validates file format (Markdown)
   - Confirms header/section structure
   - Verifies required metadata presence

3. **Content Verification**
   - Checks for required sections based on file type
   - Validates section content against expected patterns
   - Verifies internal references

4. **Consistency Verification**
   - Cross-checks information across related files
   - Validates that dates and versions align
   - Ensures no contradictory information exists

Each level builds upon the previous, with failure at any level preventing progression to the next.
**Core Memory Files**
- `memory-bank/core/active/projectbrief.md`
- `memory-bank/core/active/productContext.md`
- `memory-bank/core/active/activeContext.md`
- `memory-bank/core/active/systemPatterns.md`
- `memory-bank/core/active/techContext.md`
- `memory-bank/core/active/progress.md`

**System Files**
- `memory-bank/Bedtime Protocol/README.md`
- `.cursor/rules/main.mdc`
- `.cursor/rules/000-big-brain-identity.mdc`

**Optional But Validated If Present**
- `memory-bank/core/reference/*.md`
- `memory-bank/long-term/*/*.md`
- `memory-bank/Bedtime Protocol/*.md` (beyond README)

Missing required files trigger a critical verification failure with recovery options.
**Global Requirements**
- Valid Markdown format
- Proper heading hierarchy
- No broken Markdown syntax

**File-Specific Structure**
- `projectbrief.md`: Project overview, requirements, constraints
- `productContext.md`: Problem space, solution approach, user experience goals
- `activeContext.md`: Current focus, recent changes, next steps
- `systemPatterns.md`: Architecture, component relationships, patterns
- `techContext.md`: Technology stack, tools, environment
- `progress.md`: Feature status, open issues, milestones

Structure validation failure indicates a potentially corrupted or improperly formatted file.

Read the full file on GitHub · 397 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 · 397 lines · 0 tokens per session scan A 816eece29114

Subscribe to this mod's changes

100-memory-file-verification 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 2,692 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.