assessor-lookup-public: Skill for Claude Code

.agents/skills/appraisal-check/SKILL.md

appraisal-check is a skill for Claude Code, Codex from chadru/assessor-lookup-public. It costs 54 tokens per session (461 once invoked), scanned A, original, MIT.

A checking tool for an appraiser's MLS export, which is a spreadsheet of property listings, and county assessor records. It compares the subject property and comparable properties field by field.

In plain words
What is it for?
Use it with subject and comparable CSV files to identify discrepancies, explain common causes, and provide county record links for verification.
Why use it?
It highlights differences in living area, bedrooms, bathrooms, year built, and basement details before those differences reach an appraisal report.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is chadru/assessor-lookup-public's own configuration. It tells Claude Code and Codex how to work on assessor-lookup-public itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything assessor-lookup-public configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/chadru/assessor-lookup-public/codex/public-release/.agents/skills/appraisal-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chadru/assessor-lookup-public

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for appraisal-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/chadru/assessor-lookup-public/appraisal-check/github.svg)](https://agentmods.dev/skills/chadru/assessor-lookup-public/appraisal-check)
Your own site
<a href="https://agentmods.dev/skills/chadru/assessor-lookup-public/appraisal-check"><img src="https://agentmods.dev/badge/skills/chadru/assessor-lookup-public/appraisal-check/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.

agentmods 80×15 button for appraisal-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/chadru/assessor-lookup-public/appraisal-check"><img src="https://agentmods.dev/badge/skills/chadru/assessor-lookup-public/appraisal-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 461 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00054 $0.00461
Opus 5 $0.00027 $0.00230
Sonnet 5 $0.00011 $0.00092
Haiku 4.5 $0.00005 $0.00046

Measured 12d ago against content hash dce71f5c8c11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

appraisal-check 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 12d 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.

.agents/skills/appraisal-check/SKILL.md · 39 lines

What it actually says

Appraisal public-records check

Goal: turn an MLS export into a field-by-field discrepancy report against the county's public records, so the appraiser fixes mismatches before the report ships.

Steps

  1. Identify the county. It is auto-detected from the CSV County column; if absent, ask or infer. Confirm it is covered with list_counties. If it is not, run the onboard-locale skill first (a single county is fine).

  2. Run the check with the MCP tool check_mls_csv(subject_csv, comps_csv, county, state). The subject CSV's first row is the subject; the comps CSV holds comparables. Standard PPMLS and RESO/REColorado column names are both understood. (CLI equivalent: assessor-lookup check subject.csv comps.csv --county "<County>".)

  3. Report the discrepancies. For each property, show the flagged fields. Focus on the stable fields — GLA, beds, baths, year built, basement — where flag is true; those are the real discrepancies to reconcile. Values, owner, and taxes drift legitimately year to year, so don't alarm on those. Include the assessor_url for any flagged property so the appraiser can verify the record.

  4. Explain the common ones. Multi-level homes (tri-level, 4-level) routinely show a large GLA diff because MLS counts the lower level as basement while the assessor counts it above-grade — flag it as expected, not an error. Bath counts often differ (assessor total vs MLS above-grade split).

Principle

Report what the records actually say. Note any property that came back not_found or timeout so the appraiser checks it manually — don't silently drop it.

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. 12d ago First seen · 39 lines · 54 tokens per session scan A dce71f5c8c11

Subscribe to this mod's changes

appraisal-check is a skill published in the GitHub repository chadru/assessor-lookup-public (6 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 461 once invoked, about $0.0003 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.

Related

Other skills, from other repositories