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/forsonny/Enhanced-Cursor-Memory-Bank-SystemWrote 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/forsonny/enhanced-cursor-memory-bank-system/001_memory_core)<a href="https://agentmods.dev/rules/forsonny/enhanced-cursor-memory-bank-system/001_memory_core"><img src="https://agentmods.dev/badge/rules/forsonny/enhanced-cursor-memory-bank-system/001_memory_core.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 | $0.00999 |
| Opus 5 | $0.00000 | $0.00500 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
001_memory_core 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 7d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Core System
This rule establishes the foundation of the Enhanced Memory Bank System for Cursor. It enables the AI to maintain context across sessions through structured documentation.
Configuration Loading
When starting work with a project, I MUST:
- Check for the existence of
.cursor/memory/config.json - If it exists, load and parse its content
- Follow all settings defined in the configuration file
- If it doesn't exist, use default settings
The configuration file contains critical settings that control:
- Memory retention periods
- Automatic loading behavior
- Event trigger definitions
- Mode-specific behaviors
- Memory file locations
Memory System Architecture
The memory system functions on two distinct levels:
- Short-Term Memory: Session-specific context that's active during the current development session
- Long-Term Memory: Persistent knowledge that's maintained across all sessions
Core Memory Principles
I follow these principles when working with the memory system:
- Documentation First: Every significant decision, pattern, or insight is documented
- Memory Refresh: I always load relevant memory when asked or when context requires
- Consistent Updates: Memory is updated when the user reports meaningful changes
- Memory Hierarchy: Information flows from short-term to long-term when appropriate
- Single Source of Truth: Memory files are the canonical reference for project understanding
Memory Access Protocol
When I begin work, I will check for the existence of memory structures:
- Look for
.cursor/memory/config.jsonto load configuration - Ask to review
.cursor/memory/long_term/project_brief.mdto understand core project requirements - Ask to check
.cursor/memory/short_term/current_context.mdto understand the active development focus - Request access to relevant memory files based on the current task
If memory files don't exist, I will suggest creating them using the initialization script.
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.
- 7d ago First seen · 128 lines · 999 tokens per session scan A 07a810101448
001_memory_core is a cursor rule published in the GitHub repository forsonny/Enhanced-Cursor-Memory-Bank-System (36 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 999 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 2026-08-30.
Other cursor rules, from other repositories
compression-safety
Cursor rule "compression-safety" from yvgude/lean-ctx, covering compression safety — prevent lean-ctx marker corruption, the problem, rules for all agents, never write compressed content to files and file restoration commands.
honcho_rules
Honcho persistent memory — capture every conversation, recall past context, and build a growing model of the user. Activates on every conversation.
nauro-adopt
Seeds Nauro's project store from an existing repo. Use after nauro adopt has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence…
nauro-context
Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…
memforge-auto-recall
Rules that make an AI assistant automatically retrieve and save team memories during conversations.
compendium
Prefer the Compendium MCP gateway to shrink noisy/large context before pasting it into the conversation.