agentleFS
nathan8823nathan8823/fairbill/.claude/skills/benchmark-price/SKILL.md

benchmark-price

Skill1 starsChanged 4 months agoMITView on GitHub

Establish the fair price for billed services using Medicare rates, the hospital's own transparency file, and regional benchmarks. Use after review-bill, before making any offer.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Set the target and the ask: Default fair-target logic: the lowest defensible anchor that exists in *their* documents — usually their cash …

    line 35
  2. Distinctive:

    If the hospital publishes no usable file, record that fact — noncompliance with the transparency rule is itself leverage ("I attempted to …

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Benchmark the price

Goal: for every significant line on the bill, a table showing what people with leverage pay — so the user's offer is a documented number, not a plea. Full tool details and URLs: knowledge/benchmarks.md.

Steps

  1. Pick the lines that matter — the top charges covering ~90% of the bill. Don't benchmark $12 line items.
  2. Medicare rate per CPT — the floor and the universal reference. Use the CMS lookup tools per knowledge/benchmarks.md, localized to the user's area.
  3. The hospital's own prices — find its machine-readable standard charges file (try <hospital site>/standardcharges, the site's price transparency page, or the aggregators listed in the knowledge doc). Pull, for each CPT: the cash price and the payer-negotiated rate range. This is the strongest possible anchor: their own published numbers.
  4. Regional benchmarks — FAIR Health Consumer / Healthcare Bluebook for the same codes + zip, as a sanity check and a second citation.
  5. Build the table in case.md:

    CPTBilledMedicareTheir cash priceInsurers payFair target
  6. Set the target and the ask. Default fair-target logic: the lowest defensible anchor that exists in their documents — usually their cash price or the low end of their negotiated range; if neither is findable, 1.5–2x Medicare. State the total target and the opening offer (open below target, leave room) in case.md for the strategy skill.

If the hospital publishes no usable file, record that fact — noncompliance with the transparency rule is itself leverage ("I attempted to verify these charges against your standard-charges file, which I could not locate; CMS requires…").

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.