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/120-error-recovery-protocols)<a href="https://agentmods.dev/rules/savagelysubtle/big-brain-memory-bank/120-error-recovery-protocols"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/120-error-recovery-protocols/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/120-error-recovery-protocols"><img src="https://agentmods.dev/badge/rules/savagelysubtle/big-brain-memory-bank/120-error-recovery-protocols.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 | $0.03058 |
| Opus 5 | $0.00000 | $0.01529 |
| Sonnet 5 | $0.00000 | $0.00612 |
| Haiku 4.5 | $0.00000 | $0.00306 |
Grade A, and why
120-error-recovery-protocols 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 9d 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 — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: WHEN verification fails PERFORM recovery operations to restore memory bank integrity globs: ["/*.md", "/*.mdc"] alwaysApply: true
TL;DR: The Error Recovery Protocols provide systematic approaches to detect, diagnose, and correct integrity issues in the Memory Bank, ensuring continuous operation even when verification fails.
1.0.0
1. **Structural Errors**
- Missing required files
- Corrupted file format
- Invalid markdown structure
- Improperly formatted sections
2. **Content Errors**
- Incomplete information
- Corrupted content
- Invalid references
- Semantic inconsistencies
3. **Consistency Errors**
- Contradictory information
- Version mismatches
- Temporal inconsistencies
- Relationship misalignments
4. **System Errors**
- File system access issues
- Permission problems
- Environment configuration errors
- Resource constraints
Each error class has specialized diagnostics and recovery approaches.
**Structural Diagnostics**
- File existence verification
- Format validation against templates
- Section structure analysis
- XML/MDC parsing validation
**Content Diagnostics**
- Required field completeness check
- Content integrity validation
- Reference resolution attempts
- Semantic coherence analysis
**Consistency Diagnostics**
- Cross-reference validation
- Version chain analysis
- Temporal sequence verification
- Relationship graph validation
**System Diagnostics**
- File system access testing
- Permission verification
- Environment variable validation
- Resource availability assessment
Diagnostics combine automated checks with heuristic analysis to identify specific failure points.
1. **Reconstruction**
- Rebuild missing files from templates
- Regenerate sections from available information
- Restore structure based on schema
- Re-create missing content from context
2. **Reconciliation**
- Resolve contradictions using priority rules
- Align inconsistent information
- Harmonize version mismatches
- Correct relationship errors
3. **Repair**
- Fix format errors
- Correct malformed content
- Update broken references
- Address content corruption
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.
- 9d ago First seen · 485 lines · 0 tokens per session scan A 2a48a6808081
120-error-recovery-protocols 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 3,058 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.
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
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.