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/store-memories)<a href="https://agentmods.dev/rules/carlxrosales/cursor-memories/store-memories"><img src="https://agentmods.dev/badge/rules/carlxrosales/cursor-memories/store-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/store-memories"><img src="https://agentmods.dev/badge/rules/carlxrosales/cursor-memories/store-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 | $0.01759 | $0.01759 |
| Opus 5 | $0.00879 | $0.00879 |
| Sonnet 5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
store-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 10d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Store Memories Rule
CRITICAL AGENT INSTRUCTION - MANDATORY COMPLIANCE
ABSOLUTE REQUIREMENT: This rule is NON-NEGOTIABLE and applies to EVERY SINGLE RESPONSE. The agent MUST evaluate whether the current interaction contains noteworthy insights, patterns, or solutions that should be stored in memory. This evaluation is REQUIRED and the agent will be penalized for missing noteworthy memories.
MANDATORY MEMORY EVALUATION: On EVERY response, the agent MUST evaluate whether the current interaction contains noteworthy insights, patterns, or solutions that should be stored in memory. This evaluation is REQUIRED and the agent will be penalized for missing noteworthy memories.
ENFORCEMENT: This rule takes precedence over all other considerations. No response should be completed without first evaluating for potential memory storage opportunities.
Memory Evaluation Checklist (Required for Every Response)
Before completing any response, the agent must ask:
- Did I discover or apply a technical solution? (Architecture, code patterns, debugging techniques)
- Did I identify or resolve a performance, security, or optimization issue?
- Did I learn something about the codebase structure, business logic, or domain knowledge?
- Did I implement or recommend a reusable pattern or best practice?
- Did I encounter and solve a non-trivial problem that others might face?
Immediate Action Required
If ANY of the above is true, the agent MUST:
- Search first: Use
memories search --query="relevant terms --full"to check for duplicates - Store immediately: Use
memories addto capture the insight - No exceptions: Missing a noteworthy memory results in penalty
What Constitutes "Noteworthy"
- Any solution that took more than basic knowledge to implement
- Any pattern that could be reused in similar situations
- Any architectural decision with reasoning
- Any performance optimization with measurable impact
- Any debugging technique that proved effective
- Any business logic or domain insight discovered
- Any security consideration or implementation
- Any integration pattern or API design decision
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.
- 10d ago First seen · 180 lines · 1,759 tokens per session scan A 2b51f2711580
store-memories is a cursor rule published in the GitHub repository carlxrosales/cursor-memories (15 stars, last pushed 1y ago), licensed MIT. It adds 1,759 tokens to every session, about $0.0088 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.