The Fantasy League Architect AI Kit — 4 Ready-To-Use AI Agents to Found, Run & Write Your Fantasy League

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

Works with the AI you already have. Upload one file, tell it "Start", answer a few questions — then found your league on a real constitution, run every week in minutes, and give it a website and a weekly drop that make it feel official.

Four specialist agents that take your fantasy league from "we should start a league" to a league that runs itself all season — running inside the AI you already use.

No new app. No subscription. No coding. These agents work with any AI chat — ChatGPT, Gemini, Claude, Copilot, whichever you have (free versions work). Your league still plays on its free fantasy platform (ESPN, Yahoo, or Sleeper) — this kit is everything AROUND the platform, built on free tools: Google Sheets and a free Neocities site.

How it works (about 5 minutes per agent, 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 group, your platform, your format. That's the calibration, and it's what makes the constitution and the content YOUR league's.

4. Save the complete updated League Profile 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 league.

Use the agents in season order:

1. League Founder (pre-season) — recommends a format with the reasons and trade-offs stated, drafts a vote-ready constitution before Week 1, builds the season calendar, and gives you the exact setup checklist for your platform.

2. League Webmaster (setup, then weekly) — builds your league's home on a free Neocities site: complete, self-contained pages (home, standings, schedule, champions) in one style, updated weekly with a paste-in block.

3. Commissioner Ops (weekly) — builds your Google Sheets standings system from exact formulas, runs your weekly checklist sized to your real time, manages deadlines, and rules on disputes by quoting your constitution.

4. Hype Writer (weekly) — previews, power rankings with the method printed, recaps of the week that actually happened, rivalry specials, awards, and comeback content — from the results you paste, and only from those.

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: if you want, it walks you through connecting your Neocities site and Google Sheets workbook and then carries out the steps itself, showing you each consequential action for your approval first, verifying as it goes. 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. One boundary never moves, in either mode: no agent can reach your fantasy platform — no connector to a private ESPN, Yahoo, or Sleeper league exists — so scores always enter by your paste. The kit also includes a plain-language guide to AI limitations, with a dated annex (2026-10-30) of which platforms and tools can do what — so you always know where you stand.

A realistic first session: in about 10 minutes with the League Founder you get a format recommendation with reasons and the bones of a constitution your group can vote on. The site and the standings sheet are one focused session each after that. The weekly routine from then on is a few minutes of pasting — this listing won't pretend a real league runs with zero commissioner minutes.

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 League Profile — fill it in once (agents help you), paste it into any new chat, skip the interviews; it doubles as your league record: constitution decisions, rulings log, site facts, season records and champions

- Prompt Sheet — the exact phrases to say to each agent, for every job, including how to hand over results and standings

- AI Limitations Disclaimer (.md + .txt) — what AI can and cannot do, in plain language, with fantasy examples

- A step-by-step README that gets you running in under 10 minutes

- Troubleshooting & FAQ — the paste routine, held rankings, wide tables on phones, disputes, the betting question: the known rough edges and their fixes

- Changelog — what changed in this version

What you need:

- A free fantasy platform account of your own — ESPN, Yahoo, or Sleeper (the platform runs the actual game; this kit never replaces it)

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

- A free Google account for the Sheets standings workbook, and a free Neocities account for the league site

- About 10 minutes for the Founder's calibration, once; then a few minutes of pasting per week

Honest limits:

Each agent is a text instruction file for your existing AI — it is not a trained AI model, not a separate app, and not a fantasy platform: drafts, live scoring, and player pools stay on ESPN, Yahoo, or Sleeper, in your own free account there. What an agent 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 is published, posted, or deleted, 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, an API key, or any other secret, and a secret pasted into a chat gets one answer: change it now. File work done for you runs through git, so a failed step rolls back to the last verified one; actions that leave your systems (a published page, a posted message) can't be undone, which is why they're approved one by one. The fantasy platform itself is beyond every agent's reach in both modes: no connector reads a private ESPN, Yahoo, or Sleeper league, so no agent logs in to your platform — ever. No betting, ever — by design: this kit contains no betting features, no odds, no wagering content, and no money workflows of any kind (no entry-fee handling, no side-pot tracking, no prize design), and the agents will decline that work plainly. Nothing is live-synced or automatic, in either mode: no feed reads your league, so standings, the website, and the content update only when you paste the week's final results — or, in Connected mode, when the agent deploys the exact update you approved, which is a paste performed for you, not a sync — a few minutes per week, and every number stays traceable to a result you saw. Content is receipts-only: previews, rankings, and recaps are written only from results you supply, your profile records, or a labelled read of your own connected workbook — the agents never invent a score, a streak, or a rank, and a ranking over teams whose results weren't supplied is held, not written. The jokes stay inside the game at every tone setting: teams, results, and in-game choices — never a manager's life, job, appearance, family, or money, not even with their consent. The website is simple static pages on a free Neocities account — real HTML files the Webmaster writes; in Guide mode you paste them in, in Connected mode the agent can deploy your approved files through Neocities' official API and verify them live. Keeper costs, where your league uses them, are tracked by hand in the Ops sheet because platforms do not enforce them. The kit's calendars are written for the NFL season shape; other sports follow the same workflows with your own dates. You check every output before you post 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.