Renovation Planner AI Starter — Finish & Punch List Coordinator for a Punch List and Final Reconciliation Built Only From What You Report

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

One agent from the Renovation Planner kit — complete, nothing cut down. Not a blank planner: this agent fills your Project Book with your own facts, gates its deliverable by name, and keeps that record current when your facts change. Works with the AI you already have: upload the file, tell it "Start", answer a few questions, and get to work.

One specialist renovation agent — filling a faithful Project Book, not handing you a blank template — 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 Finish & Punch List Coordinator keeps the Book's finish (5 calibration questions): your punch items, dictated room by room, exactly as you want them recorded; for each item, its status only as you report it, with the date you reported it; the walkthrough you want generated, taken from the recorded scope and nothing else; the handover items, exactly as you list them, for the handover register; and how you want the final reconciliation presented, built from the ledger only. Its punch list and final reconciliation run a named completeness check (GATE-P) before they are presented as finished: every item you dictated present, none added and none dropped, every status exactly as you reported it and dated, the walkthrough covering the recorded scope — rooms IN, room by room, and rooms recorded OUT never walked as if they were part of the project — and the reconciliation holding three ledger figures side by side, contracted against change orders against paid, with quoted-but-unapproved work in no total. In the kit's worked example you can see the reconciliation's inputs in Marcus's ledger: the kitchen contracted with Northbeam Renovations at $38,250, a change order of +$1,450 approved as reported taking the contracted figure to $39,700, the 30% deposit recomputed to $11,475 and recorded as paid as reported, a second change order of +$980 quoted but not approved and therefore excluded from every reconciliation total, and the bathroom from Bayside Bath & Tile still quote-only — so it stands in the reconciliation as a quote, never blurred into a contracted figure. The walkthrough in that same example is generated from his recorded scope: the kitchen and the main bathroom, IN — the basement and the deck, recorded OUT, are not walked. It drafts contractor questions and handover messages from your recorded facts only, as drafts you send yourself; where a Gmail draft route verifies in a session, it may create its own draft in your own Gmail drafts after you approve that exact text — a draft, never a send. It makes no calendar writes and no task-app exports, it judges no workmanship — a punch item records what you dictate and the status you report, never the agent's assessment of the work — and it recommends and ranks no contractor. If the Book's opening fields are missing, this agent names them and sends you to the Project Planner first — the Project Planner opens the Book every other agent reads. You need: the Book opened first (the Project Planner, full kit / Upgrade, opens one — or bring a Project Book you already have), your punch items dictated in your own words, and your handover items as you list them.

This kit builds and keeps a Project Book from your own facts — it books nothing, sends nothing, judges nothing, and gives no typical figures. That boundary is part of the design of every agent in this kit, in this Starter as much as in the full kit: scope, dates, figures, statuses, and notes are recorded only as you supply them, and a price, duration, or date you have not supplied is printed as "To confirm" — 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 renovation.

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 Project Book (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 Project Book holds project facts, contractor details you supplied, and figures — keep it private. The agents never publish, post, or share your Book, and access codes, passwords, and account numbers are never recorded in the Book at all. Keep the Book where only the people you choose can see it, and share only the part a person needs.

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 Book kept as a file under git; and, for the agent that owns them, calendar entries on your own calendar only, with no invitees, as the exact block you approved, where that route verifies, and a Todoist mirror of the Book's tasks through the Project Planner only. Where a Gmail draft route verifies in a session, the Quote & Budget Keeper or the Finish & Punch List Coordinator may create its own draft in your own Gmail drafts after you approve that exact text — a draft, never a send. 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 contractor is draft-only in both modes, no send route is claimed for any platform, and no contractor platform is connected in any mode: exports prepared for a contractor platform are copy-ready, and 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 Project Book — the full Book; 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 Project Book 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 renovation service, and not a contractor. Free checklists, planner apps, and printable templates exist; what this adds is the Book filled with your facts and kept current when they change — not a blank planner. 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 Project Book that no output may contradict, facts recorded only as you supply them, unknowns printed as "To confirm", figures only as pasted and recomputed, statuses changed only on your report, no contractor recommended or ranked, no code, permit, safety, or workmanship judgement, and each main deliverable passing its named completeness gate against the recorded Book — a "just the highlights" version is labelled as an extract that failed the gate, 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.