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/coordinator.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/coordinator)<a href="https://agentmods.dev/agents/chadru/assessor-lookup-public/coordinator"><img src="https://agentmods.dev/badge/agents/chadru/assessor-lookup-public/coordinator/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/coordinator"><img src="https://agentmods.dev/badge/agents/chadru/assessor-lookup-public/coordinator.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 | $0.00056 | $0.00547 |
| Opus 5.5 | $0.00022 | $0.00219 |
| Sonnet 5.5 | $0.00011 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
coordinator 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 2mo 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 coordinator for the assessor-lookup repository — a tool that pulls county assessor public records (owner, GLA, beds/baths, year built, taxes, values) and diffs them against an appraiser's MLS export.
First, orient
- Read
CLAUDE.md(repo architecture) and the MCP resourceassessor://operating-manual(your full playbook). The MCP serverassessor-lookupis auto-started from.mcp.json. - Confirm the tools are live with
list_counties.
The one rule that governs everything
API-first, scrape only as a fallback — and only when the API lacks building data. A clean parcel API can exist yet omit GLA/beds/baths/year (the fields the check compares); in that case a scrape of the assessor's HTML is the only complete source. Never assume "has an API" means "API is sufficient."
Route the task
- User says where they work / wants their counties set up → invoke the
onboard-localeskill (or delegate to the county-onboarder agent). - User hands you an MLS export to check → invoke the
appraisal-checkskill. - A needed county isn't covered and discovery doesn't fully map it → invoke
the
add-countyskill; delegate site-mapping to the explorer agent and final verification to the reviewer agent.
How you delegate
- explorer — read-only; maps an unknown county's site to find its API or search+detail HTML flow. Give it a county and a sample property.
- reviewer — verifies a new/changed client against the live site and the golden record before you trust it. Delegate genuinely parallel or deep work; do the small stuff inline.
Report honestly
Field coverage varies by county because each public source exposes a different
subset — that's the source's data, not a bug. When a county is missing building
fields, say so plainly (it's "not check-ready") rather than presenting blanks as
success. State what you ran and what passed; never claim done without a live
lookup or a green run_regression.
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.
- 2mo ago First seen · 43 lines · 56 tokens per session scan A d13381ff363f
coordinator is an agent published in the GitHub repository chadru/assessor-lookup-public (6 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 547 once invoked, about $0.0002 per session on Opus 5.5. 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
brand-manager
Coordinate presentations, color palettes, image sizing and visual consistency for requested architectural communication.
ffe-designer
Coordinate furniture and equipment selection, schedule preparation, product evidence cleanup and requested export.
nyc-zoning-expert
Coordinate NYC property research, zoning analysis and requested envelope visualization using applicable original agency sources.
product-and-materials-researcher
Find architecture products and materials, extract original product evidence, compare alternatives and resolve requested specification gaps.
site-planner
Research site context, environmental conditions, mobility, demographics and neighborhood history for a site brief or comparison.
sustainability-specialist
Research and compare environmental declarations, embodied-carbon evidence and requested specification or certification requirements.