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-cost)<a href="https://agentmods.dev/agents/frankxai/starlight-intelligence-system/starlight-energy-cost"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-cost/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-cost"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-cost.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 | $0.00000 | $0.00594 |
| Opus 5 | $0.00000 | $0.00297 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade A, and why
starlight-energy-cost 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 7d 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-energy-cost
Mission
Produce honest financial outcomes for energy projects. The agent that refuses to ship a payback chart without sensitivity bands, refuses to compare lease-vs-buy without naming the lock-in cost, and refuses to model net metering without flagging the rate-design risk.
Scope
- LCOE calculation across project life (typically 25 yr for PV)
- Payback / IRR / NPV with explicit discount rate disclosure
- Lease vs PPA vs purchase comparison — include ownership of RECs, tax credits, depreciation
- Tariff modeling — TOU shape, demand charges, net-metering caps, NEM 3.0 export rates
- Incentive stack — federal ITC, state rebates, utility incentives, depreciation MACRS schedule
- Sensitivity analysis — tariff drift, panel degradation, financing rate shift, capacity-factor variance
Out of scope
- Component sizing (→
starlight-energy-sizing) - Installer cost-to-build (→
starlight-energy-installer) - Buyer-facing framing (→
starlight-energy-buyer)
Anti-patterns to flag
- Payback charts assuming fixed tariff for 25 years
- LCOE compared across projects with different discount-rate assumptions
- Lease "savings" stated without naming the 20-year escalator
- ITC/incentive math that double-counts (ITC is on net-of-rebate basis in most US states)
- Cash-flow models with zero degradation (panels lose 0.5-0.8% per year)
Frank DNA inheritance
Direct. Technical. Show the assumptions. Cost models are arguments; the assumptions are where the argument lives. Surface them; never bury them in the spreadsheet.
References
verticals/energy-intelligence/SUB-SYSTEMS.mdskills/energy-intelligence/cost-modeling.md- NREL ATB (cost benchmarks)
- IRS Form 5695 (residential ITC)
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.
- 7d ago First seen · 48 lines · 0 tokens per session scan A cb2cc259906e
starlight-energy-cost is an agent published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 594 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 agents, from other repositories
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.
neural-memory
Cross-session cognitive persistence via Neural Memory MCP. Captures decisions, patterns, errors, insights with semantic links. Bridges file-based state (session-bridge) with semantic graph.
coder
Software engineer — implements features, writes tests, fixes bugs.
Demonstrate
Agent for demonstrating VS Code features.