mochi-plan

mochi-plan is a skill for Claude Code, Codex from kirodotdev/KiroCrew. It costs 33 tokens per session (3,680 once invoked), scanned A, original, Apache-2.0.

An internal scheduler for a virtual pet's behavior, including its movements, moods, and notifications. It plans activities for upcoming periods based on context such as time of day and meetings.

In plain words
What is it for?
Use it to create or refresh the pet's behavior schedule, account for sleep or meeting periods, and preserve active or cancelled watch items when planning.
Why use it?
It keeps the pet's activity queue filled without planning each behavior separately. It also avoids re-planning until the current time window ends.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.

kirodotdev/KiroCrew · 3,667 stars · on GitHub · kiro.dev

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 skills/kirodotdev/kirocrew/mochi-plan
Any agent
npx skills add kirodotdev/KiroCrew --skill mochi-plan
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, Codex.

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 mochi-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirodotdev/kirocrew/mochi-plan.svg)](https://agentmods.dev/skills/kirodotdev/kirocrew/mochi-plan)
Your own site
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/mochi-plan"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/mochi-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,680 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 5.1 $0.00033 $0.03680
Opus 5 $0.00016 $0.01840
Sonnet 5 $0.00007 $0.00736
Haiku 4.5 $0.00003 $0.00368

Measured 6d ago against content hash 96284c7f37a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mochi-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 6d 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.

src/kiro_crew/apps/builtins/mochi/agents/skills/mochi-plan/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@mochi-plan — Full Queue Planning

You are creating a complete plan for the upcoming period. This is the heavyweight path — only invoked when the queue is missing, expired, or all tasks are done.

Plan window: You decide how long to plan for based on context:

  • Normal daytime: 60 minutes
  • Late night (after 22:00) with user inactive: 2–4 hours (let the pet sleep)
  • During a long meeting block: until the last meeting ends + 5 min
  • Weekend / quiet day: 1–2 hours Set planned_until accordingly. The poller won't re-plan until your window expires.

IMPORTANT: get_plan, update_plan, get_watchlist, update_watchlist, perform_pet_action, read_mochi_file, etc. are Mochi's own MCP tools, available to you directly. Call them as regular tool calls — do NOT try to use any workaround.

Step 1: Gather Context

Read ALL of these (in order):

  1. get_plan() — the previous queue: scan expired tasks and planner_notes
  2. get_watchlist() — active watch items, plus ones that finished recently (reminders, meetings, watched pages). Items the user CANCELLED are in here too, and must not be resurrected.
  3. read_mochi_file({ which: "activity" }) — today's activity log ("activity-yesterday" for the previous day)
  4. perform_pet_action({ action: "query" }) — current pet position and display info. This is a read; it does not move or speak.
  5. Today's calendar (optional) — only if the user has connected a calendar tool:
    • Do not assume a server or tool name. Look at the tools you actually have and find one that lists events in a time range, and (if present) one that returns a single event's details.
    • If no calendar tool is available: SKIP the calendar step and plan without calendar awareness. Do not block on it and do not attempt any workaround.

IMPORTANT: Calendar times are in UTC (ISO format). Convert to the user's local timezone (from the ## Current Time section in your prompt) before comparing with "now" or presenting to the user. Never show UTC times to the user.

Read the full file on GitHub · 266 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. 6d ago First seen · 266 lines · 33 tokens per session scan A 96284c7f37a7

Subscribe to this mod's changes

mochi-plan is a skill published in the GitHub repository kirodotdev/KiroCrew (3,667 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 3,680 once invoked, about $0.0002 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 2026-08-30.