redfin

A guide for collecting property listings from Redfin, a real-estate search website. It uses Redfin's CSV download endpoint to retrieve structured listing data.

In plain words
What is it for?
Use it to download regional listings with details such as price, bedrooms, bathrooms, size, location, MLS number, and property URL.
Why use it?
It avoids the 403 block on ordinary property-page requests and does not require a browser or login.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/agentcomputerai/torch/redfin
Any agent
npx skills add AgentComputerAI/torch --skill redfin
Clone the repo
git clone --depth 1 https://github.com/AgentComputerAI/torch

Made for: Claude Code, Codex.

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,097 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00095 $0.02097
Opus 5 $0.00048 $0.01048
Sonnet 5 $0.00019 $0.00419
Haiku 4.5 $0.00010 $0.00210

Measured 2d ago against content hash b4f06357eb14, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

redfin scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Proven scraping playbook for redfin.com listings. The HTML pages are CloudFront-blocked (403) on bare curl, but Redfin exposes a public undocumented endpoint at /stingray/api/gis-csv that returns the entire
skills/sites/redfin/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Redfin (redfin.com)

Redfin's HTML pages sit behind CloudFront and return 403 ERROR — Request blocked to plain curl, but their internal "Download All" CSV endpoint (/stingray/api/gis-csv) is wide open. One GET returns up to 350 listings with 27 columns of structured data — price, beds, baths, sqft, lat/lon, MLS#, URL, year built, HOA, etc. No browser, no captcha, no proxy.

Detection

Signal Value
CDN CloudFront (x-amz-cf-id, via: 1.1 ...cloudfront.net)
HTML on bare curl HTTP 403 "Request blocked"
API on bare curl HTTP 200 CSV
Auth None
Anti-bot on API None observed
robots.txt Disallows crawling listing pages, but /stingray/api/gis-csv is the same endpoint the site's "Download All" button hits

Architecture

The page at https://www.redfin.com/city/<region_id>/<STATE>/<City-Name> is a React SPA. The "Download All" button on the search results page issues a single request to:

GET https://www.redfin.com/stingray/api/gis-csv
  ?al=1
  &market=<market_slug>
  &num_homes=350
  &ord=redfin-recommended-asc
  &page_number=1
  &region_id=<region_id>
  &region_type=6        # 6 = city. Other types: 2 = zip, 5 = county, 1 = neighborhood
  &sf=1,2,3,5,6,7
  &status=9             # 9 = active for sale
  &uipt=1,2,3,4,5,6,7,8 # property types
  &v=8

The response is a CSV file (Content-Type: text/csv) with 27 columns. Cap is 350 listings per callnum_homes=1000 returns {"errorMessage":"Invalid num_homes argument value","resultCode":101}. The endpoint does not honor page_number > 1 for additional pages on the same query (it returns the same first 350). To get more than 350, narrow the query (by zip, neighborhood, price band, or property type).

The region_id comes straight from the canonical URL. For https://www.redfin.com/city/17151/CA/San-Francisco, region_id = 17151, region_type = 6.

Strategy used

  • Phase 0 — curl: HTML → 403 CloudFront. Tried /stingray/api/gis-csv → 200 CSV. Done.
  • Phase 1: skipped.
  • Phase 2: skipped (no browser needed).
  • Phase 3: parse CSV, normalize columns, save JSON.

Read the full file on GitHub · 158 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 158 lines · 95 tokens per session scan A b4f06357eb14

Subscribe to this mod's changes

redfin is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 4mo ago), licensed MIT. It adds 95 tokens to every session and 2,097 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

br3eze-code

AgentOS uses a modular 3-tier ReAct reasoning engine. The AI (Gemini 2.0 Flash / Claude Sonnet 4.6 / GPT-4o / Ollama) automatically discovers, chains, and executes these skills via the Tool Registry and Skill Loader.

br3eze-code/br3eze-code · 0 tokens

agentos-security-remediation

Review and remediate Dependabot and dependency vulnerabilities in AgentOS repositories. Use for critical or high-severity alert triage, dependency-path analysis, specialist assignment, secure upgrades, regression testing, rollback planning, release gates, and audit evidence.

br3eze-code/br3eze-code · 54 tokens

agentos-specialist-swarm

Coordinate AgentOS specialist work across Planner, Engineer, Accountant, Secretary, Procurement, Expeditor, Designer, and Draftsman roles. Use for role onboarding, WBS delegation, skill selection, activity tracking, handoffs, approvals, evidence, channel rendering, procurement exceptions, and project delivery…

br3eze-code/br3eze-code · 67 tokens

agentos-expeditor

Coordinate AgentOS fulfillment and delivery work with milestones, supplier and courier tracking, exception handling, recovery options, Procurement handoffs, escalation approvals, evidence, and receipt closure. Use for order delays, shipment tracking, vendor exceptions, and delivery recovery.

br3eze-code/br3eze-code · 54 tokens

agentos-planner

Plan and control AgentOS project work with tenant-scoped objectives, WBS decomposition, dependencies, milestones, critical path, resource and cost trade-offs, handoffs, and closeout. Use when creating or updating project plans, schedules, tickets, or specialist work packages.

br3eze-code/br3eze-code · 59 tokens

agentos-role-skill-factory

Create, validate, integrate, and release separate AgentOS role-skill packages with SKILL.md instructions and index.js entry points. Use when adding a specialist role, generating role metadata, wiring WBS and approval contracts, or packaging role skills for the repository.

br3eze-code/br3eze-code · 60 tokens