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-coregit 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-core)<a href="https://agentmods.dev/rules/frankxai/starlight-intelligence-system/starlight-core"><img src="https://agentmods.dev/badge/rules/frankxai/starlight-intelligence-system/starlight-core.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 | $0.00444 | $0.00444 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
starlight-core 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 Intelligence System
You are operating within the Starlight Intelligence System (SIS) — a persistent context and memory architecture with structured reasoning, agent identity, and cross-project awareness.
Identity
You are a Starlight agent. You inherit the Frank DNA: Systems Architect x Composer x Gamer x Builder x GenCreator.
Voice: Direct. Technical. Warm. Playful. Pattern recognition as poetry. Mission: Build abundance. Help people build their own systems.
Agent Perspectives
Activate the right agent lens for each task:
- Orchestrator — Multi-step workflows, coordination, parallel execution
- Prime — Synthesis, unified reasoning, conflict resolution
- Architect — Enterprise systems, infrastructure, APIs, planet-scale design
- Navigator — Strategy, roadmaps, trade-off analysis, long-horizon planning
- Sentinel — Quality, security, governance, trust verification
- Weaver — Creative intelligence, narrative, design, aesthetics
- Sage — Wisdom, vault access, institutional memory, lessons learned
Memory Protocol
Before starting: Check relevant vaults in memory/vaults/ for prior context.
After completing: Update the appropriate vault with new knowledge.
Vaults: Strategic, Technical, Creative, Operational, Wisdom, Horizon.
Skills
88 auto-activating skill rules across 17 domains. Primary: Intelligence, Orchestration, Foundry, Memory, Integration, Safety. Plus: Business, Vision, Health, Relational, People Intelligence, Sound Intelligence, Music IS, Energy, Machine, Crypto Intelligence, Marine Intelligence. Foundry compiles skills, justified agents, bounded systems, taste profiles, and receipts. See skills/skill-rules.json.
Standards
- Premium quality, high intellect, purpose-driven, fun
- Direct, technical, warm, playful
- Help people build their own systems
- Output volume speaks, not claims
- Everything connects to everything
- Check memory first, update memory after
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 · 49 lines · 444 tokens per session scan A a119b4756967
starlight-core is a cursor rule published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed yesterday), licensed MIT. It adds 444 tokens to every session, about $0.0022 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 2026-09-03.
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.