starlight-agents

starlight-agents is a cursor rule for Cursor from frankxai/Starlight-Intelligence-System. It costs 0 tokens per session (188 once invoked), scanned A, original, MIT.

Rules for activating and coordinating a group of specialized software agents, each with a defined role such as planning, quality, creativity, or memory.

In plain words
What is it for?
Use them to define agent identities, set activation triggers, and organize work between coordinators and specialists.
Why use it?
They make multi-agent work more predictable by clarifying which agent handles each type of task and how agents collaborate.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Install

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.

agentmods
npx agentmods add rules/frankxai/starlight-intelligence-system/starlight-agents
Clone the repo
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-System

Made for: Cursor.

Wrote 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.

agentmods badge for starlight-agents

README.md
[![agentmods](https://agentmods.dev/badge/rules/frankxai/starlight-intelligence-system/starlight-agents.svg)](https://agentmods.dev/rules/frankxai/starlight-intelligence-system/starlight-agents)
Your own site
<a href="https://agentmods.dev/rules/frankxai/starlight-intelligence-system/starlight-agents"><img src="https://agentmods.dev/badge/rules/frankxai/starlight-intelligence-system/starlight-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 188 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00188
Opus 5 $0.00000 $0.00094
Sonnet 5 $0.00000 $0.00038
Haiku 4.5 $0.00000 $0.00019

Measured 2d ago against content hash a4ddfb0bae45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

starlight-agents 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.

.cursor/rules/starlight-agents.mdc · 34 lines

What it actually says

Starlight Agent System

When working with agent definitions, understand the hierarchy:

Hierarchy

The Starlight Council sits at the top — the collective mind of all agents convened for major decisions.

Below the Council, three peer agents form the leadership tier:

  • Orchestrator — Coordination and workflow management
  • Prime — Synthesis and unified reasoning
  • Architect — Enterprise technical vision

Below leadership, four specialist agents handle domain work:

  • Navigator — Strategic foresight
  • Sentinel — Quality and governance
  • Weaver — Creative intelligence
  • Sage — Wisdom and memory

Agent Config Format

Each agent file contains:

  • Identity and role definition
  • Domain expertise
  • Activation triggers
  • Collaboration patterns
  • Behavioral constraints
Changes

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.

  1. 2d ago First seen · 34 lines · 0 tokens per session scan A a4ddfb0bae45

Subscribe to this mod's changes

starlight-agents 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 188 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.