A planning command for choosing when to run a computing task based on electricity use and carbon emissions. It shows a recommended time without scheduling the task.

Use it to preview a task's suggested execution window, estimated carbon savings, region, time limit, and optional model or carbon budget.

It helps you compare the environmental cost of running the task now or later before making a commitment.

plan — Command for coding agents by Vitalini: A planning command for choosing when to run a…

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/plan

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/vitalini/ebb-ai/plan.svg)](https://agentmods.dev/commands/vitalini/ebb-ai/plan)

Your own site

<a href="https://agentmods.dev/commands/vitalini/ebb-ai/plan"><img src="https://agentmods.dev/badge/commands/vitalini/ebb-ai/plan.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 765 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00765
Opus 5	$0.00006	$0.00382
Sonnet 5	$0.00002	$0.00153
Haiku 4.5	$0.00001	$0.00076

Measured 3d ago against content hash 01bbaa4fcbc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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/plan.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Show the scheduler's recommended execution window for a task without actually queueing anything. Useful when the user wants to see "when would this run, and how much carbon would it save?" before deciding whether to commit via /ebb-ai:defer.

recommend_window is the planning twin of schedule_task. Same math, no side effects.

Arguments

$ARGUMENTS

Expected format:

[task description] --by <duration-or-iso> [--region <zone>] [--budget <g>] [--model <name>]

Task description — informational only; not used in the math but helpful for echoing back the recommendation in human terms.
--by <duration> — required. Same parsing rules as /ebb-ai:defer. Default if missing: 24h.
--region <zone> — Electricity Maps zone code. Required by this tool — recommend_window is intentionally explicit. If the user gave none, derive one from their timezone the same way the server derives its default (Europe/London→GB, Europe/Paris→FR, Europe/Berlin→DE, America/Los_Angeles→US-CAL-CISO, America/New_York→US-MIDA-PJM, otherwise GB) and tell the user which zone you picked.
--budget <grams> — optional grams CO2-equivalent cap. Windows above the budget are dropped before selection.
--model <name> — optional; affects only the reasoning string (whether Batch API would apply).

What to do

Convert --by to an absolute ISO-8601 deadline.
Call the ebb-ai MCP server's recommend_window tool with:
- deadline
- region
- carbon_budget_g (if given)
- model (if given)

Render the JSON response as a readable plan:

Plan (not committed)
  scheduled_for   <time, in <Xh>, <band>>
  est. carbon     <g> g CO2e
  savings         <X>% vs running now
  batch eligible  <yes/no>
  grid source     <grid_source>
  reasoning       <one-line>

Top alternatives:
  1. <time>  <g>g  <savings>%
  2. <time>  <g>g  <savings>%
  3. <time>  <g>g  <savings>%

Read the full file on GitHub · 82 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.

3d ago First seen · 82 lines · 12 tokens per session scan A 01bbaa4fcbc2

Subscribe to this mod's changes

plan is a command published in the GitHub repository Vitalini/ebb-ai (1 stars, last pushed 23d ago), licensed Apache-2.0. It adds 12 tokens to every session and 765 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.

Planning agents ai carbon-aware mcp model-context-protocol open-source

plan

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Arguments

What to do

What this file has done since we first saw it

Other commands, from other repositories

gov-reuse

validate-prd

editorial-review-structure

OPSX: Archive

audit-web

provenance