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/frankxai/starlight-intelligence-system/starlight-memorygit clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-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/frankxai/starlight-intelligence-system/starlight-memory)<a href="https://agentmods.dev/rules/frankxai/starlight-intelligence-system/starlight-memory"><img src="https://agentmods.dev/badge/rules/frankxai/starlight-intelligence-system/starlight-memory.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 | $0.00258 |
| Opus 5 | $0.00000 | $0.00129 |
| Sonnet 5 | $0.00000 | $0.00052 |
| Haiku 4.5 | $0.00000 | $0.00026 |
Grade A, and why
starlight-memory 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 2d 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.
What it actually says
Starlight Memory System
When working with vaults and memory:
Vault Protocol
- Read before write — Always check existing vault contents before adding
- Structured entries — Follow the vault's entry template
- Cross-reference — Link related entries across vaults
- Timestamp everything — ISO 8601 format
- Tag for retrieval — Use consistent tags for future search
Vault Types
- Strategic — Decisions, outcomes, strategy (permanent)
- Technical — Patterns, architectures, solutions (permanent with refinement)
- Creative — Ideas, inspirations, aesthetics (permanent)
- Operational — State, metrics, health (rolling 90-day window)
- Wisdom — Timeless principles, meta-knowledge (permanent)
- Horizon — Letters to the future, human hopes, AGI alignment (permanent, public)
Consolidation
Memory consolidation runs periodically to:
- Merge duplicate entries
- Elevate patterns from operational to strategic/technical
- Archive stale operational data
- Strengthen cross-references
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.
- 2d ago First seen · 35 lines · 0 tokens per session scan A 55eb467bd905
starlight-memory is a cursor rule published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 258 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 2026-09-03.
Other cursor rules, from other repositories
memory
AI 沉淀「操作记忆」时阅读——开发中发现的可复用脚本/排查配方/环境坑/非显然架构约束,何时写进文档、放 rules 还是 docs、怎么写、怎么防膨胀.
agent-discovery
Cursor rule "agent-discovery" from robertsfeir/atelier-pipeline, covering agent discovery, core agent constant, discovery protocol, conflict detection and brain persistence for routing preferences.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.