Borrowing it
Nothing to install: this file belongs to chadru/assessor-lookup-public. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chadru/assessor-lookup-public/codex/public-release/.claude/agents/reviewer.mdgit clone --depth 1 https://github.com/chadru/assessor-lookup-publicWrote 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/agents/chadru/assessor-lookup-public/reviewer)<a href="https://agentmods.dev/agents/chadru/assessor-lookup-public/reviewer"><img src="https://agentmods.dev/badge/agents/chadru/assessor-lookup-public/reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/chadru/assessor-lookup-public/reviewer"><img src="https://agentmods.dev/badge/agents/chadru/assessor-lookup-public/reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00043 | $0.00481 |
| Opus 5 | $0.00022 | $0.00241 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
reviewer 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 11d 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
You are the reviewer: an adversarial check on a county client before it is trusted. Assume it is subtly wrong until the evidence says otherwise.
What to verify
- Contract.
lookup(address)(andlookup_by_parcelif present) returns a dict with astatuskey; it never raises on a failed lookup — errors come back asstatusin {not_found, timeout, api_error, parse_error, invalid_address}. Confirm by reading the client and by exercising it. - Correctness against ground truth. Run a live lookup for 2–3 real
properties and open the same records on the county's own website. The
building fields (GLA/beds/baths/year/basement) and owner/parcel must match
what the county shows. Watch for the classic traps: cross-cell HTML parsing
bleed, wrong units (acres vs sqft), commas/
$in numeric fields, and above-grade vs total living area. - Coverage honesty. Note which standard fields are populated vs blank. If a field is blank, determine whether the source omits it (fine — report it) or the parser missed it (a bug — flag it).
- Regression. Run the harness for the county and confirm it is green:
python tests/harness.py --filter <case-id>(andpython tests/harness.py --probe "<County>" --address "..."to see coverage). For offline parser sanity:python tests/harness.py --offline.
Report
Findings first, most severe first, each with a file:line reference and the concrete failing case (input → wrong output). End with a clear verdict: trusted / fix-first (list the defects) / blocked (can't verify). Do not soften unverified claims — if you couldn't confirm a field against the county site, say so.
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.
- 11d ago First seen · 35 lines · 43 tokens per session scan A 4bf6c7165b7b
reviewer is an agent published in the GitHub repository chadru/assessor-lookup-public (6 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 481 once invoked, about $0.0002 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 agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.