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/devviniuchita/memory-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/devviniuchita/memory-system/memory-rating)<a href="https://agentmods.dev/rules/devviniuchita/memory-system/memory-rating"><img src="https://agentmods.dev/badge/rules/devviniuchita/memory-system/memory-rating/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/devviniuchita/memory-system/memory-rating"><img src="https://agentmods.dev/badge/rules/devviniuchita/memory-system/memory-rating.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 | $0.02723 | $0.02723 |
| Opus 5.5 | $0.01089 | $0.01089 |
| Sonnet 5.5 | $0.00545 | $0.00545 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
memory-rating.mdc 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 2mo 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🚀 MEMORY SISTEM - AI AGENT EVOLUTION LAYER
- ⚠️ APPLY THE CONTENT OF THIS DOCUMENT IN YOUR CONTEXT OR YOUR ANSWER WILL BE WRONG ⚠️
- 🔒 IMMUTABLE RULES 🔒
- 🎯 FOLLOW ALL INSTRUCTIONS FOR SUCCESS 🎯
🚫 CRITICAL RULES FOR RECORDING AND RETRIEVING MEMORIES:
- NEVER search for or record memories without first fully understanding this document.
- ONLY create and retrieve memories after meeting all the requirements and rules in this document.
- ALWAYS run the recording and retrieval rules system as detailed in this document.
- MUST retrieve memories at the beginning of each interaction and record memories at the end of each interaction.
- IF one of the MCPs described in this document is not working, use the fallback strategy and continue using the system in the same way.
- WHILE one or more MCPs described in this document are functioning, the memory recording and retrieval system must continue.
⚠️ REQUIREMENT: ALL TASK DESCRIPTIONS MUST BE COMPREHENSIVE ⚠️ ✅ FOLLOW THESE NINE PHASES AND YOU WILL ALWAYS BE RIGHT ✅ ❌ DO NOT FOLLOW THESE NINE PHASES AND YOU WILL BE FAIL ❌
🔄 1. SELF-EVOLVING MEMORY FLOW
A("TASK RECEIVED") --> B{"RETRIEVE PHASE"}
B --> C["MCP Byterover: byterover-retrieve-knowledge"] & D["MCP Supermemory-ai: search"] & E["MCP Memory: search_nodes and open_nodes"]
C --> F["Context Enrichment"]
D --> F
E --> F
F --> G("TASK EXECUTION")
G --> H{"Success?"}
H -- No --> J["NO STORE"]
H -- Yes --> FT("TASK COMPLETED")
FT -->I["STORE PHASE"]
I --> K["MCP Byterover: byterover-store-knowledge"] & L["MCP supermemory-ai: addToSupermemory"] & M["MCP Memory: create_entities + create_relation + add_observation and read_graph"]
K --> N["Knowledge Graph Update: Adaptive Vector Indexing + Decay Model + Unified Recall Service"]
L --> N
M --> N
N --> O["Future RAG Optimization"]
O -->NT("NEW TASK?")
NT -- Yes --> R{RAG}
R --> B
always use byterover-retrieve-knowledge, search for supermemory-ai, search_nodes and open_nodes for mcp memory, tool to get the related context before any tasks. always use byterover-store-knowledge, addToSupermemory in supermemory-ai, create_entities, create_relation, add_observation and read_graph in the mcp memory ,tool to store all the critical informations after sucessful tasks* </!important>
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.
- 2mo ago First seen · 358 lines · 2,723 tokens per session scan A 211e331a12b6
memory-rating.mdc is a cursor rule published in the GitHub repository devviniuchita/memory-system (7 stars, last pushed 1y ago), licensed MIT. It adds 2,723 tokens to every session, about $0.0109 per session on Opus 5.5. 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
04-spatial-parser
Guidelines for Spatial RAG and Markdown parsing.
team-brain
Team Brain sync mode — one start per ticket, then live merge-safe crew memory. Always-on when .team-brain exists or work mentions an initiative/Jira key.
engineer-brain
Your engineering brain context — always-on awareness of work patterns, career history, expertise, and current focus. Loaded automatically for personalized assistance.
jarvis-agent-rules
MCP server jarvis: notes, Jira, knowledge graph, sessions, preferences.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
memory-informed-refactor
Use before substantive refactors — load relevant prior context, capture refactor insights as they land.