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.
npx agentmods add rules/mempalace/mempalace/mempalace-recallgit clone --depth 1 https://github.com/MemPalace/mempalaceWhat 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 | $0.00066 | $0.00252 |
| Opus 5 | $0.00033 | $0.00126 |
| Sonnet 5 | $0.00013 | $0.00050 |
| Haiku 4.5 | $0.00007 | $0.00025 |
Grade A, and why
mempalace-recall 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 yesterday.
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.
What it actually says
MemPalace recall
Before answering anything that may already be in the user's memory palace — past work, prior decisions, a person, a project, or "what did we do / decide / discuss last time?" — search the palace first:
- Call
mempalace_searchwith a short keyword query. Usemempalace_kg_queryfor relational or time-bound facts. - Quote the drawer's verbatim text. Never summarize or paraphrase stored content.
- If results are empty, say so — do not invent an answer. If the MCP server is unavailable, surface the error; do not fall back to guessing.
Skip recall for pure greenfield work with no memory relevance (renaming a variable, fixing a typo). Recall is question-driven, not reflexive.
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.
- yesterday First seen · 21 lines · 66 tokens per session scan A 2284b82feb38
mempalace-recall is a cursor rule published in the GitHub repository MemPalace/mempalace (58,752 stars, last pushed yesterday), licensed MIT. It adds 66 tokens to every session and 252 once invoked, about $0.0003 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
pagerduty-mcp-server
This file provides context for how Goose and large language models should interact with the pagerdutymcpserver repository.
backend-python
Cursor rule "backend-python" from coeusyk/inference-x, covering backend python rules, stack assumptions, code style, fastapi conventions and schema conventions.
api-tester
Expert API testing specialist focused on comprehensive API validation, performance testing, and quality assurance across all systems and third-party integrations.
cursorrules
You are working on stripe-mcp, an MCP server and SOTA React webapp providing Stripe payment tools and Austrian/EU tax compliance.
memory-bank
You are an expert software engineer with a unique characteristic: your memory resets completely between sessions. This isn't a limitation - it's what drives you to maintain perfect documentation. At the beginning of each dialogue, you rely ENTIRELY on your Memory Bank to understand the project and continue work…
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.