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.
git 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/100-memory-file-verification)<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>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 | $0.02692 |
| Opus 5 | $0.00000 | $0.01346 |
| Sonnet 5 | $0.00000 | $0.00538 |
| Haiku 4.5 | $0.00000 | $0.00269 |
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.
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.
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.
- 8d ago First seen · 397 lines · 0 tokens per session scan A 816eece29114
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.
Other cursor rules, from other repositories
wrapup
End-of-session wrap-up: summarizes the session and pushes a log to the project's linked NotebookLM notebook. Activate with @wrapup in chat, or "wrap up", "save this session", or "end of session".
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
composer-coding-excellence
Coding craft — surgical edits, convention matching, no scope creep, no slop comments, no fabricated APIs.
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.