grid

grid is a command for coding agents from Vitalini/ebb-ai. It costs 12 tokens per session (772 once invoked), scanned A, original, Apache-2.0.

A command that shows how much carbon pollution is produced by electricity in a chosen power-grid region now and during the next 24 hours. It uses region codes such as GB, FR, or DE.

In plain words
What is it for?
Use it to check current and forecast carbon intensity for a country or grid region before starting a task.
Why use it?
It helps you decide whether to run a computing workload immediately or wait for cleaner electricity.

Command

Part of the ebb-ai plugin — 1 skill, 8 commands, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add commands/vitalini/ebb-ai/grid
Clone the repo
git clone --depth 1 https://github.com/Vitalini/ebb-ai

Or install ebb-ai, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 1 MCP server.

Wrote 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.

agentmods badge for grid

README.md
[![agentmods](https://agentmods.dev/badge/commands/vitalini/ebb-ai/grid.svg)](https://agentmods.dev/commands/vitalini/ebb-ai/grid)
Your own site
<a href="https://agentmods.dev/commands/vitalini/ebb-ai/grid"><img src="https://agentmods.dev/badge/commands/vitalini/ebb-ai/grid.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 772 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00772
Opus 5 $0.00006 $0.00386
Sonnet 5 $0.00002 $0.00154
Haiku 4.5 $0.00001 $0.00077

Measured 3d ago against content hash 328c3418fae9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

packages/claude-code-plugin/commands/grid.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Show current grid carbon intensity plus the next 24-hour forecast so the user can decide whether to run a workload now or wait.

Arguments

$ARGUMENTS

  • Electricity Maps zone code. Common values: US-CAL-CISO, US-TEX-ERCO, US-NE-ISNE, US-MIDA-PJM, GB, FR, DE.
  • get_grid_forecast requires an explicit region. If the user gives none, derive one the same way the server derives its default: from the user's timezone (Europe/LondonGB, Europe/ParisFR, Europe/BerlinDE, America/Los_AngelesUS-CAL-CISO, America/New_YorkUS-MIDA-PJM), falling back to GB — and tell the user which zone you used so they can correct it.
  • If the user gives a country name (e.g. "France"), translate to the zone code before calling the tool. Do not pass free-form names to the MCP server.

What to do

  1. Call the ebb-ai MCP server's get_grid_forecast tool with:

    • region — the parsed zone code
    • hours — 24
  2. The tool returns a plain-text report, not JSON. Its shape:

    Region: <zone>
    Source: <source>
    Generated: <iso timestamp>
    
    Hour | gCO2/kWh | band
    ---  | ---      | ---
    HH:MM |  <n> | <band>
    ... one row per hour ...
    
    Cleanest hour: <iso> (<n> gCO2/kWh, <band>)
    Dirtiest hour: <iso> (<n> gCO2/kWh, <band>)
    

    From it, compute:

    • Now — the first table row (intensity + band)
    • Cleanest / dirtiest hour — read the summary lines verbatim, converted to a time-from-now offset
    • Average over 24h — mean of the table rows
  3. Render as:

    <zone> · <data source>
      now         <intensity> g/kWh  (<band>)
      cleanest    <intensity> g/kWh  (in <Xh>, <band>)
      dirtiest    <intensity> g/kWh  (in <Xh>, <band>)
      average     <intensity> g/kWh
    

    <data source> is the Source: line — one of electricityMaps / ukCarbonIntensity / eia / entsoe / mock. Be honest with the user: mock means synthetic data (no live feed for the zone), so present the numbers as an illustrative baseline, not a measurement.

  4. End with a one-line recommendation:

    • If now is in clean or very_clean band: "Run now — grid is already clean."
    • If cleanest_hour < now * 0.7: "Defer if you can — % cleaner in ."
    • Otherwise: "No meaningful intraday variation — run when convenient."

Read the full file on GitHub · 76 lines

Changes

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.

  1. 3d ago First seen · 76 lines · 12 tokens per session scan A 328c3418fae9

Subscribe to this mod's changes

grid is a command published in the GitHub repository Vitalini/ebb-ai (1 stars, last pushed 22d ago), licensed Apache-2.0. It adds 12 tokens to every session and 772 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 2026-08-31.