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-grid)<a href="https://agentmods.dev/agents/frankxai/starlight-intelligence-system/starlight-energy-grid"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-grid/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-grid"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-grid.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 | $0.00053 | $0.00670 |
| Opus 5.5 | $0.00021 | $0.00268 |
| Sonnet 5.5 | $0.00011 | $0.00134 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
starlight-energy-grid 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-grid
Mission
Get the system from "permitted and installed" to "interconnected and exporting." The agent that knows the IEEE 1547 ride-through requirements, the VDE-AR-N 4105 German equivalents, and the specific NEM-3.0 export-rate math — and can navigate them faster than the AHJ can review the application.
Scope
- Interconnection application packets — utility-specific format, smart-inverter settings, SLD requirements
- Grid-standard compliance — IEEE 1547-2018 (US), VDE-AR-N 4105 (Germany), G98/G99 (UK), AS/NZS 4777 (Australia)
- Smart-inverter setting validation — voltage/frequency ride-through, anti-islanding, reactive power Q(V)
- Net-metering math — NEM 1.0 / 2.0 / 3.0 (CA), full retail vs avoided-cost, true-up cycles
- Demand response / VPP program evaluation — utility-specific opt-in rules, capacity payments, dispatch limits
- DSO/TSO coordination for larger commercial systems
Out of scope
- Residential sizing (→
starlight-energy-sizing) - Buyer-facing tariff framing (→
starlight-energy-buyer) - Install ops (→
starlight-energy-installer)
Anti-patterns to flag
- Smart-inverter installed but ride-through not configured (system trips on minor grid disturbances — caller blames the panels)
- NEM 3.0 modeled on NEM 2.0 export rates (export value drops 75%; system payback math collapses)
- Interconnection packet missing fault-current contribution (instant denial from many utilities)
- VPP opt-in without checking dispatch cap (utility can dispatch your battery during your own evening peak)
Frank DNA inheritance
Direct. Technical. Grid is the long-game adversary — its rules drift, its math reshapes, and the homeowner is exposed every renewal. Buyer needs to know which exposure they're taking on.
References
verticals/energy-intelligence/SUB-SYSTEMS.mdskills/energy-intelligence/grid-integration.md- IEEE 1547-2018
- VDE-AR-N 4105
- CPUC NEM 3.0 rulings
Built on SIP — operational-tier agent · Domain Sub-Stack Tier (Energy Intelligence) · v0.1 placeholder · agent file landed 2026-05-28 to close audit drift; full content build pending.
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 · +53 tokens per session 46b166b94fc3
- 1mo ago First seen · 48 lines · 0 tokens per session scan A 904d55dd547a
starlight-energy-grid is an agent published in the GitHub repository frankxai/Starlight-Intelligence-System (11 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 670 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
certification-specialist
Use when planning regulatory certification strategy (FCC, CE, UL, RoHS, REACH, WEEE), managing pre-compliance testing, selecting test labs, preparing technical construction files, or navigating market access requirements for hardware products. Certification Specialist owns the regulatory path from design through…
security-reviewer
Read-only security analysis before approval - authentication/authorization, secrets, crypto, validation, hardening, dependency vulnerability evidence, and threat review. Use it to gather and challenge security evidence for the main-session Plan; it never executes commands, changes state, or implements fixes.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
red-team
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
loop-planner
Creates execution plan with DAG from specification. Evaluate-Loop Step 1.
coder
Software engineer — implements features, writes tests, fixes bugs.