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.
npx skills add FernanMoreno/DomoAI --skill battery-arbitragegit clone --depth 1 https://github.com/FernanMoreno/DomoAIWrote 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/skills/fernanmoreno/domoai/battery-arbitrage)<a href="https://agentmods.dev/skills/fernanmoreno/domoai/battery-arbitrage"><img src="https://agentmods.dev/badge/skills/fernanmoreno/domoai/battery-arbitrage/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/skills/fernanmoreno/domoai/battery-arbitrage"><img src="https://agentmods.dev/badge/skills/fernanmoreno/domoai/battery-arbitrage.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 | $0.00022 | $0.00604 |
| Opus 5 | $0.00011 | $0.00302 |
| Sonnet 5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
battery-arbitrage 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Battery arbitrage
This procedure keeps battery optimization proposal-only until the runtime has qualified actuator bindings, limits and readable power feedback.
Declared operations
discover_devicesget_stateget_energy_contextoptimize_scenariovalidate_planexplain_solutionoperator_approvalcommit_or_schedule_bundle
Operation bindings
discover_devices→mcp.discover_devices(read)get_state→mcp.get_state(read)get_energy_context→mcp.get_energy_context(read)optimize_scenario→mcp.optimize_scenario(proposal)validate_plan→mcp.validate_plan(validation)explain_solution→mcp.explain_solution(read)operator_approval→operator.request_approval(approval)commit_or_schedule_bundle→mcp.commit_or_schedule_bundle(mutation)
Procedure
discover_devices— identify a qualified battery and canonical charge/discharge/stop routes.get_state— read SOC, availability and numeric power feedback; stop when stale or unavailable.get_energy_context— read tariffs, solar and terminal SOC policy for the horizon.optimize_scenario— produce a bounded dispatch proposal only.validate_plan— require actuator qualification, feedback postconditions and current dependencies.explain_solution— show SOC limits, terminal reserve and forecast assumptions.operator_approval— request approval for the exact bundle if physical mutation is allowed.commit_or_schedule_bundle— delegate to admission, fencing and readback.
Safety rules
- Non-zero battery dispatch without explicit actuator binding is analysis-only.
- Missing/stale/invalid/mismatching power feedback confirms neither success nor failure; use
UNKNOWN. - Never cross SOC, power, thermal or terminal-reserve limits.
- A forecast or SOC value is not authority and cannot replace commissioning.
- Do not retry after an unknown inverter write without reconciliation evidence.
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.
- 4d ago First seen · 59 lines · 22 tokens per session scan A 1e32e122770e
battery-arbitrage is a skill published in the GitHub repository FernanMoreno/DomoAI (0 stars, last pushed 5d ago), licensed MPL-2.0. It adds 22 tokens to every session and 604 once invoked, about $0.0001 per session on Opus 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 2026-09-08.
Other skills, from other repositories
augur-serenity
Serenity AI — AI/semiconductor supply chain bottlenecks, chokepoint assets.
electric-truck-readiness
Use when a carrier asks about electric trucks — Tesla Semi, Freightliner eCascadia, Volvo VNR Electric, Peterbilt 579EV, range, charging, total cost of ownership, regulatory pushes (CARB ACT, ACF), incentives, infrastructure, depot vs en-route charging, and which routes/applications are EV-ready today.
downtime-cost-calculator
Calculate and analyze the true cost of equipment downtime, enabling farmers to make informed decisions about repair, replacement, and preventive maintenance investments.
recurring-revenue
Designs the recurring revenue layer for hardware companies: software license, maintenance and support, consumables, professional services, and data/insights tiers. Models LTV, defines the Year-1 bundling strategy, and builds the commoditization defense. A hardware company that sells only hardware has a lumpy…
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.