plan-day

plan-day is a command for Claude Code from gonnagetapower/kelvia-mcp. It costs 12 tokens per session (256 once invoked), scanned A, original, MIT.

A command that builds a daily work plan in Kelvia, a task-board and planning tool. It reviews today’s plan, overdue time blocks, and board tasks before proposing new time blocks for approval.

In plain words
What is it for?
Choosing realistic tasks for a day, estimating their time, leaving slack for interruptions, and creating approved planning blocks.
Why use it?
It prevents double-booking, overloading the workday, and blindly carrying every overdue item forward.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the kelvia plugin — 1 skill, 4 commands shipped together

Good fit Choosing realistic tasks for a day, estimating their time, leaving slack for interruptions, and creating approved planning blocks.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gonnagetapower/kelvia-mcp/plan-day
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.

Clone the repo
git clone --depth 1 https://github.com/gonnagetapower/kelvia-mcp

Made for: Claude Code.

Or install kelvia, the plugin that ships this one along with the rest of its 1 skill, 4 commands.

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 plan-day

README.md
[![agentmods](https://agentmods.dev/badge/commands/gonnagetapower/kelvia-mcp/plan-day/github.svg)](https://agentmods.dev/commands/gonnagetapower/kelvia-mcp/plan-day)
Your own site
<a href="https://agentmods.dev/commands/gonnagetapower/kelvia-mcp/plan-day"><img src="https://agentmods.dev/badge/commands/gonnagetapower/kelvia-mcp/plan-day/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.

agentmods 80×15 button for plan-day

Your own site · 80×15
<a href="https://agentmods.dev/commands/gonnagetapower/kelvia-mcp/plan-day"><img src="https://agentmods.dev/badge/commands/gonnagetapower/kelvia-mcp/plan-day.svg" alt="Reviewed on agentmods" width="80" 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 256 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.00256
Opus 5 $0.00006 $0.00128
Sonnet 5 $0.00002 $0.00051
Haiku 4.5 $0.00001 $0.00026

Measured 10d ago against content hash ac68c550ee1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

plan-day 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 10d 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.

plugin/commands/plan-day.md · 28 lines

What it actually says

Turn the board into a realistic plan for today.

  1. Check what is already planned: list_daily_plan_blocks for today, and list_overdue_daily_plan_blocks for what slipped from earlier days. Never plan over existing blocks without saying so.

  2. Read the board with list_tasks and pick candidates: what is in progress, what is due, what is blocking someone else.

  3. Propose the plan as a list of time blocks before creating anything. State how long each will take and why that task made the cut. Ask the user to adjust.

  4. On confirmation, create the blocks with create_daily_plan_block.

Rules for the plan itself:

  • Leave gaps. A plan with no slack fails at the first interruption, and then the whole plan gets abandoned rather than adjusted.
  • Do not schedule more hours than remain in the working day.
  • Overdue blocks are a signal, not a backlog to re-add wholesale. Ask before carrying them forward — some of them should be dropped instead.

If $ARGUMENTS names a date or a focus, plan for that instead of today's default.

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. 10d ago First seen · 28 lines · 12 tokens per session scan A ac68c550ee1e

Subscribe to this mod's changes

plan-day is a command published in the GitHub repository gonnagetapower/kelvia-mcp (1 stars, last pushed 26d ago), licensed MIT. It adds 12 tokens to every session and 256 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.