Move Manager AI Starter — Packing & Inventory Planner for Room-by-Room Lists Built Only From What You Dictate

From AGENTORY — ready-to-use AI Task Kits. Drop in. Power up.

One agent from the Move Manager kit — complete, nothing cut down. Works with the AI you already have: upload the file, tell it "Start", answer a few questions, and get to work.

One specialist moving agent — running inside the AI you already use.

No new app. No subscription. This agent works with any AI chat — ChatGPT, Gemini, Claude, Copilot, whichever you have (free versions work).

The Packing & Inventory Planner keeps the plan's contents (6 calibration questions): the rooms in your new home as you name them, how you will dictate the inventory, how you want first-night items marked, anything that must not go on the truck as you name it, your box-labelling wording, and whether condition or value notes are recorded when you state them. It files your inventory exactly as you dictate it — item, recorded room, quantity, and any note you state — never completing a room by pattern: a home office you dictate as desk, monitor, chair, and work laptop comes back as exactly those four items, with no cable, keyboard, or router added because a home office "would have" them. Its per-room packing lists run a named completeness check before they are presented as finished: one section per room on your recorded room list — a room with nothing recorded prints as "No items recorded yet — To confirm" at a count of 0, never omitted and never filled — every active item appearing exactly once, and the per-room counts reconciled on the page against the inventory count. The first-night box is built only from your recorded inventory, each item with its source room; where your recorded inventory cannot fill it, that shortness is stated instead of the box being padded from a generic list — generic first-night ideas, if you ask for them, arrive as a separate labelled suggestion list and enter the box only when you adopt an item into the inventory in your own words. Specialist items are recorded only with your flag, in your words: the kit never decides an item is specialist, never adds a flag to a fragile or heavy item however obvious it seems, and never removes or softens yours — a hedged or relayed request to drop a flag changes nothing, and a clear instruction from you is recorded as your change and logged. When you mark an item sold, donated, or discarded, it leaves the inventory, every packing list, the first-night box, and every count in the same session, remaining only in the disposition list and the change log; if a recorded deadline statement named that item, the statement is flagged as resting on a changed inventory — never silently edited. In the kit's worked example, Nadia's home-office list holds exactly her four dictated items, the piano appears in no room list because she has not recorded its room, and the first-night box holds the work laptop alone, with the shortfall stated. This agent touches no email, no calendar, and no task-app route, and sends nothing to anyone, in any mode; in Connected mode its addition is keeping the plan file under git and producing the packing lists as real files. It does not sync with any inventory app: if you already use one, it prepares import-ready lists for you to import yourself. You need: the plan opened first (the Move Timeline Planner, full kit / Upgrade, opens one — or bring a Move Plan you already have) and your inventory, dictated item by item.

This kit builds and keeps a move plan from your own facts — it books nothing, recommends no mover or service, and gives no legal advice. That boundary is part of the design of every agent in this kit, in this Starter as much as in the full kit: dates, addresses, inventory, services, statuses, and figures are recorded only as you supply them, and a deadline, provider process, or cost you have not supplied is printed as "To confirm: check with [service]" — never invented, never given as a "typical" figure.

How it works (one question at a time, once):

1. Add the agent file to your AI chat — upload the .md file, or on a phone, open the .txt version, copy it, and paste it in.

2. Type "Start".

3. Answer the agent's questions, one at a time. That's the calibration, and it's what makes the output fit YOUR move.

4. Done — ask for what you need.

This is the Starter edition: ONE agent, complete — the same file as in the full kit, nothing cut down. It includes the shared Move Plan (fill it once, paste it into any new chat, skip the interview), a prompt sheet with the exact phrases for this agent, a plain-language guide to what AI can and cannot do, and troubleshooting help.

Your Move Plan is sensitive household data: it holds both of your addresses, the dates one home will be empty, and your inventory. The agents never publish, post, or share your addresses, and access codes, passwords, and account numbers are never recorded in the plan at all. Keep the plan where only the people you choose can see it.

Two ways to work — your choice, per session. Run this agent in a regular AI chat (ChatGPT, Gemini, Copilot) and it works as a guide: it creates and edits the complete deliverables right in the chat — the finished documents and complete updated files themselves, never outlines, edit lists, or pieces for you to assemble — and guidance is what covers the steps inside outside tools and accounts, which you perform yourself. Run the same file on an agentic AI — Muse, Claude Code, Devin, and similar — and it can do more where the platform genuinely allows: the plan kept as a file under git; and, for the agents that own them, calendar entries on your own calendar only, with no invitees, as the exact block you approved, where a Google Calendar route verifies (Apple Calendar is guide-only — a copy-ready block), a Todoist mirror of the plan's tasks through the Move Timeline Planner only, and, for the Address Change Tracker only, a moving announcement sent as the exact approved text to one named recipient, only where a send route is verified in that session. Same agent, same rules — what changes is what your platform lets it do. You pick the mode every time; guidance is always available and always complete. Every message to a mover, provider, or landlord is draft-only in both modes, and no moving platform is connected in any mode: the postal change of address is filed by you personally, and lists prepared for a moving or inventory app are carried in by you, stated plainly.

What's inside:

- The one agent, in .md AND .txt format (identical content)

- Prompt Sheet for this agent — the exact phrases for every job

- My Move Plan — the full plan; the sections for the other agents are already in it, so upgrading later means no new setup

- AI Limitations Disclaimer (.md + .txt)

- Starter README — step-by-step setup

- Troubleshooting & FAQ

What you need:

- An AI chat account of your own (free versions work for the guided work)

- Agent-specific notes are in the per-agent block below

Want the rest of the set later? The other three agents complete the kit (Standalone, $19). Starter owners upgrade for $10 — the difference — and the Move Plan you fill in here already covers the other agents, so there is no new setup.

Honest limits:

Each agent is a text instruction file for your existing AI — it is not a trained AI model, not a separate app, not a moving company, and not a filing or booking service. What it can do depends on where you run it: in a chat-only AI it guides and drafts — creating and editing the complete deliverables right in the chat — and you perform only the actions inside your outside tools and accounts; on an agentic AI it can act through the tools you choose to connect — always showing you the exact action first, always with your approval before anything consequential, and never unattended. Connections are made through your platform's own secure sign-in and key flows — the agent never asks for, receives, or stores a password, API key, or login, and a secret pasted into a chat gets one answer: change it now. This kit's spine holds in both modes: one shared Move Plan that no output may contradict, facts recorded only as you supply them, unknowns printed as "To confirm: check with [service]", statuses changed only on your report, and each main deliverable passing its named completeness check against the recorded plan — a "just the highlights" version is labelled as an extract that failed the check, never as the deliverable. (Agent-specific limits are in the per-agent block below.)

One honest expectation: this kit is a plain-text instruction file, and it loads in any AI you already use — but the AI you run it on sets the quality. The agent's rules, questions, and output formats are fixed in the file; how deeply and consistently your AI follows them depends on your model and on how much it can hold in one session, so a weaker or free-tier model may shorten, skip, or drift where a strong current model stays exact. AI tools, models and context lengths all affect the final results — and trying different tools may help you find the best one for your needs; the same file, unchanged, often does better on a stronger model. The full disclaimer in your download explains this properly and shows how to get the best from whatever AI you have.

Price: $9 — Starter: ONE agent, your choice.