shearline: Skill for Claude Code

.claude/skills/hail-claim-verification/SKILL.md

hail-claim-verification is a skill for Claude Code from lostnumber07/shearline. It costs 59 tokens per session (808 once invoked), scanned A, original, MIT.

A procedure for checking whether hail occurred at a specific place and date by comparing storm reports with radar information. The result is an evidence-based indication, not a legal ruling.

In plain words
What is it for?
Use it for insurance claims, roofing or vehicle damage disputes, and questions about whether hail actually fell at a location on a particular day.
Why use it?
It helps assess hail-damage claims when the reported event needs independent support, while showing the distance and time of available evidence.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is lostnumber07/shearline's own configuration. It tells Claude Code how to work on shearline 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 shearline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lostnumber07/shearline. 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/lostnumber07/shearline/main/.claude/skills/hail-claim-verification/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lostnumber07/shearline

Made for: Claude Code.

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 hail-claim-verification

README.md
[![agentmods](https://agentmods.dev/badge/skills/lostnumber07/shearline/hail-claim-verification/github.svg)](https://agentmods.dev/skills/lostnumber07/shearline/hail-claim-verification)
Your own site
<a href="https://agentmods.dev/skills/lostnumber07/shearline/hail-claim-verification"><img src="https://agentmods.dev/badge/skills/lostnumber07/shearline/hail-claim-verification/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 hail-claim-verification

Your own site · 80×15
<a href="https://agentmods.dev/skills/lostnumber07/shearline/hail-claim-verification"><img src="https://agentmods.dev/badge/skills/lostnumber07/shearline/hail-claim-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 808 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 $0.00059 $0.00808
Opus 5 $0.00030 $0.00404
Sonnet 5 $0.00012 $0.00162
Haiku 4.5 $0.00006 $0.00081

Measured 11d ago against content hash 1c2a571daa3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hail-claim-verification 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.

.claude/skills/hail-claim-verification/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hail-claim verification

Goal: produce a defensible corroborated / partially corroborated / not corroborated verdict for a hail claim at a specific location and date, with the evidence and its distance/time from the claimed loss.

Reminder: SHEARLINE data is informational and preliminary (NWS/spotter reports), not a legal adjudication or the final NCEI Storm Events record. State that in the output.

Inputs you need

  • Location — a street address or place. Geocode it to lat, lon (decimal degrees, CONUS only; longitude is negative in the US).
  • Date of the alleged hail — a single UTC calendar day, YYYY-MM-DD. If the claimant gives a local date/time near midnight, check the adjacent UTC day too.
  • Claimed hail size (optional, inches) — to compare against reports.

Procedure

  1. Pull ground-truth reports for that day. get_historical_storm_reports(lat, lon, date, radius_km=40)

    • Read data.counts.hail and the data.reports entries with category: "hail".
    • For each hail report note magnitude (inches), time_utc, and distance_km / direction from the claim location.
  2. If the event was within the last ~24 hours, add radar-derived hail. get_mrms_severe(lat, lon, radius_km=40)

    • data.hail_mesh.max_mesh_in is the radar Maximum Estimated Size of Hail in the last hour, with the distance/bearing of the maximum. (MRMS only retains ~24–48 h, so this step applies to recent claims only; for older dates rely on step 1.)
  3. Widen if nothing close. If no hail report is within ~15 km, re-run step 1 with radius_km=80 to see whether a hail swath passed nearby (hail is highly localized; a report 30 km away is weak support).

  4. Form the verdict.

    • Corroborated — a hail report (or MESH ≥ 1") within ~15 km and within a few hours of the claimed time, of comparable or larger size.
    • Partially corroborated — hail reported in the broader area (15–40 km) or of smaller size than claimed.
    • Not corroborated — no hail reports within 40 km on that UTC day (note that pre-2005 dates aren't covered, and an empty old-date result is not proof of a quiet day).

Read the full file on GitHub · 62 lines

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. 11d ago First seen · 62 lines · 59 tokens per session scan A 1c2a571daa3a

Subscribe to this mod's changes

hail-claim-verification is a skill published in the GitHub repository lostnumber07/shearline (0 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 808 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.