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.
npx agentmods add commands/zeropointrepo/zillow-plugin/compsgit 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/comps)<a href="https://agentmods.dev/commands/zeropointrepo/zillow-plugin/comps"><img src="https://agentmods.dev/badge/commands/zeropointrepo/zillow-plugin/comps.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 | $0.00020 | $0.00363 |
| Opus 5 | $0.00010 | $0.00181 |
| Sonnet 5 | $0.00004 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
comps 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 3d 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
Run sold comps for the subject property: $ARGUMENTS
Steps (uses the zillapi MCP server; ~10–15 credits total for a normal run):
- Identify the subject property from the input above. If none was given, ask for a U.S. address or zillow.com link — do not guess.
- Pull the subject's full record —
lookup_property_by_zpidif you have a zpid from a Zillow URL (1 credit), otherwiselookup_property_by_address(3 credits). Note its lat/lon, beds, sqft, and Zestimate. - Call
search_listingswithstatus: "sold", a tight bounding box around the subject's lat/lon (±0.01–0.02°, roughly a 1–2 km radius), andbeds_minone below the subject's bedroom count. Each result costs 1 credit, so keep the box tight; widen only if fewer than 3 comps come back. - Build the comp table: address, sold price, beds/baths, sqft, $/sqft, distance from subject. Drop obvious non-comparables (wrong home type, sqft off by more than ~40%).
- Conclude with: median $/sqft of the comps × subject sqft = indicated value, shown next to the Zestimate and (if listed) the asking price. Note this is an estimate from public data, not an appraisal.
If a 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.
- 3d ago First seen · 17 lines · 20 tokens per session scan A 899e34a7b2b0
comps is a command published in the GitHub repository ZeroPointRepo/zillow-plugin (0 stars, last pushed 10d ago), licensed MIT. It adds 20 tokens to every session and 363 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
research
Professional equity research analysis with institutional-grade formatting.
swarm
Fan out a parallel review across the workspace using Kimi's AgentSwarm tool, bounded by a hard wall-clock budget. Read-only by default (enforced by the same PreToolUse hook as review, applied to every subagent); --write fans out edits in a throwaway worktree and returns a patch.
tasse
Stima imposta sostitutiva, INPS e acconti del forfettario (principio di cassa).
cogs-sentinel
Use when AI 기능의 단가·사용량·가격으로 p50/p90 월간 마진을 결정해야 합니다. hplan/cogs-sentinel wrapper는 lognormal sampler와 free-user abuse blend로 GREEN/CONDITIONALGO/RED를 판정합니다.
pm-burn
Cost burn-rate — LLM cost over the last N days vs a human-equivalent baseline (savingsx). Flags cost outliers and abnormal-burn agents.
radar-start
启动 BTC News Radar 的采集与看板.