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.
git clone --depth 1 https://github.com/ZeroPointRepo/zillow-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/zeropointrepo/zillow-plugin/search)<a href="https://agentmods.dev/commands/zeropointrepo/zillow-plugin/search"><img src="https://agentmods.dev/badge/commands/zeropointrepo/zillow-plugin/search.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00023 | $0.00298 |
| Opus 5 | $0.00012 | $0.00149 |
| Sonnet 5 | $0.00005 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
search scanned grade A with 0 findings 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 6d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Search Zillow listings for: $ARGUMENTS
Steps:
- Parse the request above into: an area, a status (
for_saledefault; usefor_rentorsoldwhen asked), and optionalbeds_min/price_max. If no area was given, ask for one — do not guess. - Convert the area to a bounding box
"west,south,east,north"in decimal degrees for thesearch_listingstool on thezillapiMCP server. Size it to the area named: neighborhood ≈ ±0.02°, city ≈ ±0.05–0.15°. Keep it tight — each returned listing costs 1 credit, so before calling, tell the user roughly how many results to expect and narrow if the request is broad. - Call
search_listingswithbbox,status, and any filters. - Present results as a compact table: address, price, beds/baths, sqft, and zpid. Offer to pull the full record for any of them (
lookup_property_by_zpid, 1 credit).
If the tool call fails with an authentication error, tell the user to complete the Zillapi OAuth sign-in prompt (free account, 100 credits, no card) and retry.
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.
- 6d ago First seen · 16 lines · 23 tokens per session scan A 991af6f4f5cd
search is a command published in the GitHub repository ZeroPointRepo/zillow-plugin (0 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 298 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
check
Run proctor against the current changes and report what it found.
setup
Set up proctor in this repository: the git pre-commit hook, plus the ruleset for every agent in use.
posthog:llma-cc-ingest
Manually send a Claude Code session log to PostHog LLM Analytics.
posthog:llma-cc-setup
Set up PostHog LLM Analytics to capture Claude Code sessions.
posthog:llma-cc-status
Check if Claude Code sessions are being sent to PostHog LLM Analytics.
init
Install the formatters this repository needs, with every command visible before it runs.