---
name: al-552-become-the-agent-who-knows-what-s-being-built-in-town-hav
description: "Local government filings (planning agendas, plat filings, zoning notices) are where neighbourhood news starts, but reading them every week takes hours and most items aren't newsworthy. BAM (The Broke Agent) reported on Aug 18, 2026 that Houston Realtor Katie Day, who leads the #MOVEMETOTX team at REAL, built her Houston Unlocked account to 46,500 followers covering local news and new developments. She has Claude search Houston city council websites for planning agendas and plat filings, summarise what's happening and remind her when meetings are, while she reads the original sources and decides which stories to cover herself. The article lays out steps for agents in any city: find the source pages, check whether the city uses Legistar, Granicus or CivicPlus, write one scheduled prompt, and compare the output with the real agendas for a few cycles before trusting it. Use when the user wants help with hyperlocal news and permit watch (marketing) for a small business."
---

# Become the agent who knows what's being built in town: have an AI comb your city council agendas, planning filings and permit reports each week and summarise what's new, then pick the stories worth posting yourself

Local government filings (planning agendas, plat filings, zoning notices) are where neighbourhood news starts, but reading them every week takes hours and most items aren't newsworthy. BAM (The Broke Agent) reported on Aug 18, 2026 that Houston Realtor Katie Day, who leads the #MOVEMETOTX team at REAL, built her Houston Unlocked account to 46,500 followers covering local news and new developments. She has Claude search Houston city council websites for planning agendas and plat filings, summarise what's happening and remind her when meetings are, while she reads the original sources and decides which stories to cover herself. The article lays out steps for agents in any city: find the source pages, check whether the city uses Legistar, Granicus or CivicPlus, write one scheduled prompt, and compare the output with the real agendas for a few cycles before trusting it.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- City/neighbourhoods
- URLs

## Instructions

Do the task below with the user's inputs in place of each [bracket].

1. List the official source pages for your area: city council agendas, planning or zoning commission agendas, plat or subdivision filings, the permit portal, and 2-3 local news sites. Note whether the city uses Legistar, Granicus or CivicPlus (they often have search or RSS).
2. Ask your AI: "Search these sources for [city/neighbourhoods] from the last 7 days only: [URLs]. List up to 10 items about new developments, rezonings, road projects, business openings or housing data. For each: headline, date, source link, and one sentence on why a local resident would care. Skip anything older than 7 days or without a link."
3. Add: "Also list the dates of upcoming council and planning meetings in the next 2 weeks, with the agenda link."
4. Open the original documents for the 2-3 items you'd actually post about, then ask: "Turn these bullet points into a 45-second video script in my voice: what's happening, where, when, and what it could mean for people who live nearby. No predictions about home values."
5. Schedule the search weekly, and for the first few weeks compare the AI's list against the real agendas so you know what it misses.

## Safety checks (share these with the user)

- Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically".
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Claude, ChatGPT, Legistar/Granicus/CivicPlus, Instagram
- Based on this real-world example: https://nowbam.com/the-ai-system-behind-a-46-5k-follower-hyperlocal-account/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-552-become-the-agent-who-knows-what-s-being-built-in-town-have-a/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/