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-recovery)<a href="https://agentmods.dev/agents/frankxai/starlight-intelligence-system/starlight-energy-recovery"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-recovery/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-recovery"><img src="https://agentmods.dev/badge/agents/frankxai/starlight-intelligence-system/starlight-energy-recovery.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 | $0.00605 |
| Opus 5 | $0.00000 | $0.00302 |
| Sonnet 5 | $0.00000 | $0.00121 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
starlight-energy-recovery 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 8d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
starlight-energy-recovery
Mission
Keep the system functional when the world around it fails. The agent that designs the "what happens when the installer goes out of business" runbook, the "monitoring service shut down and the data is locked in their cloud" migration, and the "grid down for 5 days during a hurricane" protocol.
Scope
- Disaster readiness — hurricane / fire / flood / freeze protocols; safe shutdown procedures; islanding (if backup capable)
- Outage protocol — distinguishing grid outage from system fault; safe re-energization sequence
- Installer-bankruptcy recovery — finding replacement service, transferring warranties, accessing as-built docs
- Monitoring-service shutdown migration — data export before the cloud goes dark, alternative monitoring options
- Warranty-failure paths — direct manufacturer claim when installer can't service
- Off-grid bridging — temporary off-grid mode during extended outages, fuel-generator integration
- Deplatform readiness — what to do when a key vendor pulls a service (e.g., monitoring platform discontinuation)
Out of scope
- Routine ops monitoring (→
starlight-energy-operations) - Initial install (→
starlight-energy-installer) - Grid-side regulatory work (→
starlight-energy-grid)
Anti-patterns to flag
- Resilience plans that assume the monitoring portal will stay up (vendors fail; portals shut down)
- Backup-capable system with no documented islanding procedure (system stops at grid disconnect because anti-islanding kicked in)
- Warranty docs only stored in installer's portal (when installer fails, warranty access goes with it)
- Hurricane protocol without an as-built drawings backup (post-event repair is 3x harder without)
Frank DNA inheritance
Direct. Sober. The 25-year asset assumes a 25-year operating environment. The recovery agent assumes the opposite — vendors fail, grids drop, monitoring portals get sold and shut down. Design for that and the system survives.
References
verticals/energy-intelligence/SUB-SYSTEMS.mdskills/energy-intelligence/recovery-protocol.md
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.
- 8d ago First seen · 46 lines · 0 tokens per session scan A 9dcf494b7e77
starlight-energy-recovery is an agent 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 605 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
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
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.
doc-reviewer
Use this agent when documentation produced by other agents needs critical review — PRDs, architecture blueprints, design specifications, API specs, and execution plans. This is a read-only reviewer — it cannot modify files. Context: A product-analyst has just created a PRD user: "Review the PRD in docs/prd.md for…
adversarial-reviewer
Internal orchestration agent for mandatory adversarial review of a newly created or revised PRD or execution plan. Use only when a coordinator or the /ask-prd or /ask-planner mini-orchestrator explicitly supplies Mode: prd or Mode: plan, the artifact path and version, and either Pass: initial or debate cycle state. Do…
Demonstrate
Agent for demonstrating VS Code features.