Renovation Planner AI Kit — Upgrade (For Starter Owners)

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

Already own one Renovation Planner Starter agent? Complete the set for the difference — and complete the filled, gated Project Book that agent started.

Already own one Renovation Planner AI Starter agent? This completes your set — and completes the Project Book, not a blank planner: the Book your Starter started filling, with its scope, dates, figures, site record, and punch items, carried into all four agents.

The full kit (Standalone) is $19. You paid $9 for your Starter — this Upgrade is the $10 difference, and it delivers the complete Renovation Planner AI Kit: all four agents (Project Planner, Quote & Budget Keeper, Site Log Keeper, Finish & Punch List Coordinator), each in .md and .txt, with the Prompt Sheet, My Project Book, the AI Limitations Disclaimer, Troubleshooting & FAQ, the README, and the changelog.

No new setup: the Project Book you filled in for your Starter already has sections for all four agents — your calibration, scope and its IN and OUT lists, supplied dates, pasted figures and change orders, dated site record, punch items and statuses, handover register, drafts, and change log carry over. Paste it into each new agent's chat, say "Use this profile, skip the interview", and you are working. One exception, stated plainly: if your Starter was not the Project Planner, the Book's cover may not be opened yet — the Project Planner opens it, and the other agents will name the missing cover fields and route you to it rather than improvising a second cover.

In short form, the boundary that defines this kit: it builds and keeps a Project Book from your own facts — it books nothing, sends nothing, recommends or ranks no contractor, and makes no code, permit, safety, or workmanship judgement and states no jurisdiction rule. That holds for every agent you are adding: a price, duration, or date you have not supplied is printed as "To confirm" and never invented, and never given as a typical figure; figures are held only as you pasted them, with totals recomputed from their shown parts and missing lines shown as "not supplied — not in this total"; site entries are verbatim, in your words, uninterpreted; statuses change only when you report them, per item and dated; a confirmed date change re-derives the schedule and flags any recorded fact it conflicts with instead of moving it; and each main deliverable — scope record, budget/quote summary, site-log weekly rollup, punch list and final reconciliation — passes its named completeness gate (GATE-S / GATE-B / GATE-L / GATE-P) against the recorded Book, with a "just the highlights" version labelled as an extract that failed the gate, never as the deliverable. The Book holds project facts, contractor details you supplied, and figures, and no agent publishes, posts, or shares them.

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: the Book kept as a file under git; calendar entries on your own calendar only, with no invitees, as the exact block you approved, created by the Project Planner only, where that route verifies; a Todoist mirror of the Book's tasks through the Project Planner only, where that platform offers the route, with the Project Book remaining the source of truth; and, where a Gmail draft route verifies in-session, creation of a draft in your own Gmail drafts by the Quote & Budget Keeper or the Finish & Punch List Coordinator, after you approve that exact text. Same agents, same rules — what changes is what your platform lets them do. Every message to a contractor is draft-only in both modes — nothing is sent, in either mode, and no send route is claimed — and no contractor platform is integrated in either mode: exports prepared for Houzz, Angi, Buildertrend, CoConstruct, JobTread, or any other contractor platform are copy-ready, and carried in by you.

What's inside: the complete Standalone kit (all four agents and every supporting document from the Standalone listing).

What you need: an AI chat account of your own (free versions work for the guided work), and one Renovation Planner Starter already purchased — this Upgrade is priced as the difference for Starter owners. If you don't own a Starter yet, the right product is the Standalone kit ($19) or a Starter ($9).

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 kit's spine holds in both modes: one shared Project Book that no output may contradict, facts recorded only as you supplied them and reproduced as supplied, unknowns printed as "To confirm" rather than completed from a pattern, figures only as pasted with totals recomputed from their shown parts and missing lines shown as missing, statuses only as you report them, changes propagated and logged — a date change re-derived in full, a recorded date never moved as a side-effect — and escalation stopping the task with a facts-only summary you carry yourself, never one the agent sends. Nothing runs unattended, and no agent ever accepts a password or secret in either mode. 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: $10 — the difference between the $9 Starter and the $19 Standalone kit.