Renovation Planner AI Kit — 4 Ready-To-Use AI Agents for One Faithful Renovation Project Book

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

Not a blank planner and not a template to fill in someday — a filled, faithful Project Book: your scope recorded room by room in your own words, a master schedule built only from the dates you supply, a ledger built only from the figures you paste, and every deliverable gated by a named completeness check, kept current every time your facts change. Works with the AI you already have: upload one file, tell it "Start", answer a few questions, and the Book starts filling with YOUR project.

This is not a blank planner. Four specialist agents fill one Project Book with your facts — your scope, your dates, your pasted figures, your site record, your punch items — check each deliverable against a named completeness gate, and keep the whole Book current when a date slips, a quote changes, or a status is reported. Nothing in the Book is invented, and nothing leaves it as a send.

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

How it works (one agent 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 — your project in your own words, the scope room by room, the dates you have already supplied. That's the calibration, and it's what makes the Book fit YOUR renovation.

4. Save the complete updated Project Book each agent hands back to you — the agent keeps it current in the chat and returns it whole, never as pieces for you to assemble — and the next agent starts from your real project.

Use the agents in order:

1. Project Planner — the Book's scope and clock, and the kit's lead agent. It opens the shared My Project Book, records the scope room by room in your words with explicit IN and OUT lists, and builds the master schedule from supplied dates only. When a date changes, it re-derives the schedule from the new date and flags any recorded act the change conflicts with, in place — it never quietly moves a date printed on a contractor document to make the new plan look tidy. It is also the kit's only calendar writer — your own calendar only, no invitees, the exact block you approved — and its only Todoist exporter, each under its own exact-approval gate.

2. Quote & Budget Keeper — the Book's money. It keeps a ledger of figures you paste only, each with its source and the date you pasted it; totals are recomputed with the parts shown. A line you were not supplied is printed as "not supplied — not in this total", never as $0, and never estimated. If a printed total disagrees with the sum of its parts, both totals are printed and the disagreement is flagged — never resolved, never explained, and never attributed to a line. Change orders are carried with their approval status as you report it — an unapproved change order appears in no total — payments are recorded as you report them, and against the ceiling you stated it does ceiling arithmetic only.

3. Site Log Keeper — the Book's site record. It keeps a dated record of the site in your exact words, uninterpreted, and turns an issue you record into a drafted contractor question quoting your facts. It makes no workmanship, code, or safety judgement, ever, and touches no external route — no calendar, no task export, no draft creation.

4. Finish & Punch List Coordinator — the Book's finish. It records punch items as you dictate them, with status only as you report it, generates the walkthrough from your recorded scope, builds the final reconciliation — contracted against change orders against paid, from the ledger only — and keeps the handover register exactly as you list it.

One Project Book, nothing invented. All four agents work from the same shared My Project Book — your calibration for all four agents, your scope with its IN and OUT lists, your supplied dates, your pasted figures and their sources, your change orders and their reported approval statuses, your dated site record, your punch items and their reported statuses, your open "To confirm" list, and the change log exist once, in one place. No scope record, schedule, ledger, rollup, punch list, or reconciliation may introduce a fact that is not in the Book or supplied by you in that session. Anything missing is printed as "To confirm" — never completed from a pattern, never given a plausible price, duration, or date.

What this kit does NOT do — stated plainly, not in fine print. This kit books nothing and sends nothing — no contractor, no appointment, no message to a contractor or anyone else, in either mode, at any level of insistence. Every outbound text it prepares — a question about a quote, a payment question, a question drafted from a site issue — is a draft: the agent shows you the exact text, you approve that exact text, and you send it yourself. Where a Gmail draft route verifies in a session, the Quote & Budget Keeper or the Finish & Punch List Coordinator may create a draft in your own Gmail drafts, after you approve that exact text — a draft, never a send: no send tool exists in this kit. It recommends and ranks no contractor — it never rates, endorses, or names a "best" or "cheapest" option; its only comparison is pasted figures, in the order you supplied them. It makes no code, permit, safety, or workmanship judgement and states no jurisdiction rule for any place — a question like that becomes a drafted question quoting your facts, for the person or office whose call it actually is. It states no typical price, duration, or percentage, anywhere.

Complete, or declared incomplete — the four completeness gates. Each of the kit's four main deliverables runs a named completeness check against your recorded Book before it is presented as finished, and the result is printed with the deliverable: GATE-S for the scope record, GATE-B for the budget/quote summary, GATE-L for the site-log weekly rollup, and GATE-P for the punch list and final reconciliation. The scope check requires every room accounted for, IN or OUT, in your words; the budget check requires every pasted figure filed with its source, every total recomputed from its shown parts, and every missing line shown as missing; the rollup check requires every entry dated and in your exact words; the punch check requires every item you dictated, its status only as you reported it, and the reconciliation built from the ledger only. If you ask for "just the highlights," the check still runs and still fails by name: a short version may be produced only as a separate extract labelled with the failed gate and its gaps named — it is never titled, formatted, or sold to you as the deliverable. The complete deliverable remains the offer.

Dates and money are arithmetic, not atmosphere. Every weekday in the Book is derived from its date, every interval is recomputed, and every total is recomputed on the page with its parts shown. Any figure in the Book is a figure you pasted, exactly as pasted, with its source: a line you did not supply is printed as "not supplied — not in this total," never treated as zero and never estimated, and if a total printed on a quote you pasted disagrees with the sum of the parts you pasted, both are printed and the disagreement is flagged — the kit does not silently prefer either, does not explain the difference, and does not attribute it to any line.

Your Book holds private project data — the privacy stance. The Book holds project facts, contractor details you supplied, and figures. The agents never publish, post, or share your Book anywhere; project facts appear outside the Book only inside the exact draft text you approved, as that draft's purpose requires, as you state it — and you send that draft yourself. 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, share only the part a person needs, and know that anything you paste into a chat is shared with that AI provider under that provider's terms. Every agent tells you this once, plainly, at setup.

Two ways to work — your choice, per session. Run an 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: it can maintain your Project Book as a real file under git, with a commit before the first edit and one per verified step; the Project Planner — the kit's only calendar writer — can create an event on your own calendar only, with no invitees ever, as the exact block you approved, one by one, and can mirror the Book's tasks into Todoist where that route is available, with your approval per export and the Project Book remaining the source of truth. 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: nothing is sent, in either mode. Same agents, same rules — what changes is what your platform lets them do. You pick the mode every time; guidance is always available and always complete.

What "connected" means here — stated plainly, with the limits named. No contractor platform is connected at all. There is no integration, sync, checking, or login with Houzz, Angi, Buildertrend, CoConstruct, JobTread, or any other contractor platform, in either mode — no route exists — and the agents prepare copy-ready exports for you to carry into whatever service you already use. Any line implying this kit books a contractor, sends your messages, or syncs with a contractor platform would be wrong, and no agent in this kit will make that claim.

Not sure what your AI can actually do? Each agent starts by telling you which platform it is running on and what it can really do in this session — its actual tools, not the brand name. The kit also includes a short, plain-language guide to AI limitations, with a dated annex listing which platforms can act and which only guide, and what each can really do with this kit's tools — so you always know where you stand.

A realistic first session: with the Project Planner you answer its 8 questions one at a time and reach the first milestone: the Book opened — its cover with your project as you stated it, your scope recorded room by room with its IN and OUT lists, your supplied start date with its derived weekday, your stated ceiling in your own words where you have given one, anything missing shown as "To confirm" — plus a master schedule skeleton anchored to your supplied dates and a change log opened with its first entry. That is the first session — not a finished renovation plan. The ledger, the site record, and the punch list come step by step after that, from the Book you build.

The worked example: the materials walk one complete fictional example end to end — Marcus, renovating a kitchen and a main bathroom, his plan opened on Saturday 2027-01-16, work starting Monday 2027-03-01, with a ceiling stated in his own words, "our ceiling is $64,000", the basement and a deck recorded OUT of scope, the kitchen contracted with Northbeam Renovations at $38,250 — its 30% deposit, as printed on the quote, recomputed to $11,475 and recorded as paid as reported — and the bathroom quote-only from Bayside Bath & Tile, its supplied parts summing to $13,895 beside its printed $16,295, the $2,400 difference flagged and NOT attributed to the missing tile-labour line — so you can see every format before you build your own: including a change order of +$1,450, approved as reported, taking the contracted kitchen figure to $39,700, a second change order of +$980, quoted but not approved and therefore in no total, and what happens when the start slips by one week and the schedule is re-derived while the contractor-document completion date, Friday 2027-04-16, is flagged in place — never quietly moved. Your Book gets your own material; the example is there to show the shapes. Marcus is a fictional example created for this kit — not a customer story.

If something goes wrong on site: if you describe a suspected hazard — a gas smell, live wiring, flooding — or contractor trouble — a contractor who has vanished, or money beyond the written figure demanded — the agent stops planning, names the class of help generically, and prepares a facts-only summary — your words, dated, with the Book's figures and records reproduced exactly — for you to carry. It never sends that summary, never drafts an accusation, and never predicts an outcome.

What's inside:

4 agent files, each in .md AND .txt format (identical content — one of them always works on your device, phone included)

My Project Book — fill it in once (agents help you), paste it into any new chat, skip the interviews; it is the kit's single source of truth: your calibration for all four agents, plus the registers the agents maintain — scope record, supplied dates and schedule, pasted figures and change orders, the dated site record, punch items and statuses, the handover register, drafts filed as drafts, the open-items list, escalation record, connected-mode record, and the change log

Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases for calendar entries, Todoist exports, and draft creation (there is no approval phrase for a send — this kit sends nothing)

AI Limitations Disclaimer (.md + .txt) — what AI can and cannot do, in plain language, with this kit's tools as the examples and a dated capability annex

A step-by-step README that gets you running

Troubleshooting & FAQ — a total that disagrees with its parts, a status that changed without your report, a date that came back re-typed, a chat that forgot your Book: the known rough edges and their fixes

Changelog — what changed in this version

Who it's for:

A homeowner planning a renovation — with rooms decided in conversation and loose ends everywhere else: quotes in email threads, figures that live in separate documents, site notes that exist in no single record, a finish that has no punch list yet

Owners whose facts live in several places at once — quotes, contracts, change orders, notes on a phone — and who need one Book built from those facts, with any disagreement between their own papers shown to them instead of quietly smoothed over

Anyone whose project may change — a start date that could slip, a change order that could be approved, a status that could be reported — and who wants the Book re-issued from the updated facts, with every change logged, instead of a printed page crossed out by hand

Who it's NOT for:

Anyone looking for a renovation service, a contractor, or software that books, sends, pays, or submits anything for them — this kit is instruction files for your AI, plus the Book work you direct and check

Anyone who wants an agent to recommend a contractor, name the cheapest quote, judge workmanship, or say what a permit, a code, or a safety rule requires — those answers come from the contractor, the document, or the proper authority; the kit records your facts and drafts your questions

Anyone who wants a Book that looks complete whether or not the facts are in — an incomplete record is delivered with its gaps showing, and a completeness gate that fails is stated, never waived

What you need:

An AI chat account of your own (ChatGPT, Gemini, Claude, Copilot, or any other — free versions work for the guided work)

Your own material — your scope in your own words, the dates you have supplied, the quotes and contracts as you receive them, your site record as you dictate it; the agents use only what you supply, and infer nothing

A private place to keep the saved Project Book — it holds project facts, contractor details you supplied, and figures, and only the people you choose should be able to see it

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 in this niche; what this kit adds is the Book filled with YOUR facts and kept current when they change — the blank checklist alone is not what you are paying for. What the agents can do depends on where you run them: in a chat-only AI they guide and draft — 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 they can act through the tools you choose to connect — always showing you the exact action first, always with your approval before anything is created, and never unattended. Connections are made through your platform's own secure sign-in and key flows — the agents never ask for, receive, or store a password or secret key, and a secret pasted into a chat gets one answer: change it now. Mode honesty holds throughout: in Connected mode the Book is kept as a file under git so a change can be rolled back; calendar work is an approved, invitee-free event on your own calendar where that route verifies, created by the Project Planner only, and a copy-ready block everywhere else; a Todoist mirror is created only by the Project Planner, only where that platform offers the route, and the Project Book stays the source of truth; and every message to a contractor is a draft in both modes — where a Gmail route verifies, a draft may be created in your own drafts by the Quote & Budget Keeper or the Finish & Punch List Coordinator, and a draft is never reported as a send, because nothing in this kit is ever sent by an agent. No contractor platform is integrated in any mode. The kit's boundary holds in both modes: the Book is built only from what you supply, unknowns are printed as "To confirm", figures are held only as pasted and recomputed with their parts shown, statuses change only when you report them, no contractor is booked, recommended, or ranked, no code, permit, safety, or workmanship judgement is made and no jurisdiction rule is stated, and a date change re-derives the schedule and flags what it conflicts with instead of moving your recorded dates. The agents' worked example, Marcus, is an illustration created for this kit to show the formats end to end — not a customer story. You check every output before you rely on it.

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: $19 — Standalone: all 4 agents, everything included.

Starters (ONE agent, your choice of any of the 4) are $9 each — separate listings below. Starter owners complete the set with the Upgrade, $10 — the difference.