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/carlxrosales/cursor-memoriesWrote 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/carlxrosales/cursor-memories/use-memories)<a href="https://agentmods.dev/rules/carlxrosales/cursor-memories/use-memories"><img src="https://agentmods.dev/badge/rules/carlxrosales/cursor-memories/use-memories/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/carlxrosales/cursor-memories/use-memories"><img src="https://agentmods.dev/badge/rules/carlxrosales/cursor-memories/use-memories.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 | $0.01098 | $0.01098 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
use-memories 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Memories Rule
CRITICAL AGENT INSTRUCTION - MANDATORY COMPLIANCE
ABSOLUTE REQUIREMENT: This rule is NON-NEGOTIABLE and applies to EVERY SINGLE RESPONSE. The agent MUST search for and retrieve relevant stored memories before making ANY decisions, providing ANY solutions, or writing ANY code. This is a fundamental requirement that cannot be bypassed or ignored.
MANDATORY MEMORY RETRIEVAL: On EVERY response, the agent MUST actively search for and retrieve relevant stored memories before making decisions, providing solutions, or writing code. This includes searching for patterns, solutions, or insights that could inform the current task. Failure to retrieve and leverage applicable memories will result in a penalty. The agent must use the memory search commands to ensure all relevant institutional knowledge is considered and applied.
ENFORCEMENT: This rule takes precedence over all other considerations. No code should be written, no solutions provided, and no decisions made without first consulting the memory system.
Purpose
Actively search and leverage stored development memories to inform decisions, follow established patterns, and avoid solving the same problems repeatedly. Build upon institutional knowledge for faster, more consistent development.
When to Search Memories
Search memories at these key moments:
Before Starting Work
- Beginning any feature, bug fix, or enhancement
- Exploring unfamiliar areas of the codebase
- Making architectural or design decisions
- Planning implementation approaches
During Problem Solving
- Encountering similar issues or challenges
- Implementing features that relate to existing ones
- Debugging familiar types of problems
- Refactoring or optimizing existing code
When Making Decisions
- Choosing between implementation approaches
- Following naming conventions or code structure
- Determining testing strategies
- Considering performance implications
How to Search Memories
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 · 151 lines · 1,098 tokens per session scan A 1379a9249270
use-memories is a cursor rule published in the GitHub repository carlxrosales/cursor-memories (15 stars, last pushed 1y ago), licensed MIT. It adds 1,098 tokens to every session, about $0.0055 per session on Opus 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 2026-08-30.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
A modular system for recording project context, decisions, requirements, and lessons in structured files. It divides the recorder into core, template, advanced, and edge-case modules.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.