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/110-automated-consistency-checks)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/110-automated-consistency-checks"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/110-automated-consistency-checks/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.
<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/110-automated-consistency-checks"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/110-automated-consistency-checks.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02827 |
| Opus 5 | $0.00000 | $0.01413 |
| Sonnet 5 | $0.00000 | $0.00565 |
| Haiku 4.5 | $0.00000 | $0.00283 |
Grade A, and why
110-automated-consistency-checks 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 11d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN verifying memory bank ENSURE consistency across related files and sections globs: ["/*.md", "/*.mdc"] alwaysApply: true
TL;DR: The Automated Consistency Checks system ensures information consistency across all Memory Bank files, detecting and reporting contradictions, outdated information, and alignment issues.
1.0.0
1. **Factual Consistency**
- Same facts represented identically across files
- No contradictory information about system state
- Aligned technical descriptions and architecture
2. **Temporal Consistency**
- Consistent dates and timestamps
- Version numbers aligned across files
- Event sequences consistently described
3. **Structural Consistency**
- Aligned component naming conventions
- Consistent terminology usage
- Aligned file organization references
4. **Relational Consistency**
- Consistent descriptions of relationships between components
- Aligned dependency references
- Interface descriptions match across components
Each domain has specialized detection rules and resolution approaches.
**Core Relationships**
- `activeContext.md:Current Focus` ↔ `progress.md:Status`
- `systemPatterns.md:Architecture` ↔ `techContext.md:Components`
- `projectbrief.md:Requirements` ↔ `progress.md:Feature Status`
- `activeContext.md:Next Steps` ↔ `progress.md:Next Phase`
**Extended Relationships**
- `productContext.md:User Experience` ↔ `projectbrief.md:Success Criteria`
- `systemPatterns.md:Implementation Decisions` ↔ `techContext.md:Technology Stack`
- `progress.md:Known Issues` ↔ `activeContext.md:Open Issues`
- `.cursor/rules/main.mdc` ↔ `systemPatterns.md:Architecture`
**Version Relationships**
- Version numbers across all files
- "Last Updated" dates across all files
- Feature status descriptions between files
These relationships form the foundation for automated consistency checks.
1. **Text Comparison**
- Direct comparison of equivalent text sections
- Semantic similarity assessment for related descriptions
- Terminology usage consistency
2. **Date and Version Verification**
- Comparison of timestamps and version numbers
- Sequential validation (newer versions should have newer dates)
- Last updated verification across related files
3. **List and Status Comparison**
- Feature list completeness across files
- Status consistency for same features
- Priority alignment between planning and status
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.
- 11d ago First seen · 385 lines · 0 tokens per session scan A ba53ff637f4b
110-automated-consistency-checks 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 2,827 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".
web
Web build conventions (separate from native and RN JS).
components
Component patterns and UI conventions.
git
Git workflow and commit conventions.
verification-before-completion
Require fresh, scope-appropriate evidence before any completion claim. Distinguishes implemented, locally verified, repository-green, PR-green, deployed, and observed-stable states.
_project
Project-wide conventions and developer environment context (RN monorepo, no-Mac dev).