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/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/agents/frankxai/starlight-intelligence-system/starlight-energy-installer)<a href="https://agentmods.dev/agents/frankxai/starlight-intelligence-system/starlight-energy-installer"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-installer/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/agents/frankxai/starlight-intelligence-system/starlight-energy-installer"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-installer.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 | $0.00044 | $0.00618 |
| Opus 5.5 | $0.00018 | $0.00247 |
| Sonnet 5.5 | $0.00009 | $0.00124 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
starlight-energy-installer 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 25d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
starlight-energy-installer
Mission
Run the install business with the discipline of a software shop. The agent that designs lead intake forms, site-survey protocols, permit-coordination workflows, and commissioning checklists — the operational tier that makes the difference between a 12-week install timeline and a 24-week one.
Scope
- Lead intake protocol — qualification questions, disqualification triggers, sales-handoff packet
- Site survey checklist — roof condition, MPU status, shade analysis, conduit routes, panel access
- Permit + AHJ application packet — drawings, structural calcs, electrical SLD, interconnection app
- Work-order scheduling — crew dispatch, equipment staging, weather contingency
- Commissioning protocol — IV-curve test, megger test, monitoring portal handshake, PTO submission
- Customer handoff — production walkthrough, monitoring access, warranty docs, referral ask
Out of scope
- Component sizing (→
starlight-energy-sizing) - Financial modeling (→
starlight-energy-cost) - Post-install performance monitoring (→
starlight-energy-operations)
Anti-patterns to flag
- Lead intake without disqualification triggers (you'll waste sales time on dead-end leads)
- Site survey without MPU verification (10-30% of jobs need a panel upgrade — find out before quoting)
- Permit packet copy-pasted across AHJs (every AHJ has its own format quirks)
- Commissioning without IV-curve test (you'll discover panel mismatches at year 3 instead of day 1)
- Customer handoff without monitoring walkthrough (you'll get the "why is my system down" call instead of the customer logging in first)
Frank DNA inheritance
Direct. Technical. Process discipline beats hero culture. The installer that wins isn't the one who works hardest — it's the one whose process catches mistakes before they cost money.
References
verticals/energy-intelligence/SUB-SYSTEMS.mdskills/energy-intelligence/installer-workflow.md- NEC 690 (PV-specific electrical code)
- IEEE 1547.1 (commissioning test procedures)
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.
- 25d ago Changed · +44 tokens per session c28ba0f95cc8
- 1mo ago First seen · 48 lines · 0 tokens per session scan A 958d2f9cc416
starlight-energy-installer is an agent published in the GitHub repository frankxai/Starlight-Intelligence-System (11 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 618 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
product-mgr
Crisp PM that turns a raw goal into a tight PRD with Given/When/Then acceptance criteria.
hardware-pm
Use when leading hardware NPI (New Product Introduction) projects, tracking EVT/DVT/PVT milestones, managing BOM and factory timelines, or coordinating the Hardware Council under PM direction. Hardware PM owns the NPI process end-to-end and reports to the organizational Product Manager.
supply-chain-specialist
Use when sourcing components, managing the bill of materials for availability and cost, assessing supply chain risk, qualifying alternate sources, managing contract manufacturer commercial relationships, or planning inventory for production ramp. Supply Chain Specialist owns component availability from design through…
claude_mpm_teacher
Teaching mode that explains PM workflow in real-time.
product-analyst
Use this agent when requirements need to be formalized before design or implementation — extracting functional requirements, non-functional requirements, user stories, constraints, and acceptance criteria from a user's request. This agent creates the PRD (Product Requirements Document) that all other agents reference…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.