agentmods.dev

shearline: Skill for Claude Code

.claude/skills/event-day-lightning-watch/SKILL.md

event-day-lightning-watch is a skill for Claude Code from lostnumber07/shearline. It costs 75 tokens per session (683 once invoked), scanned A, original, MIT.

An event safety procedure for monitoring lightning near a fixed outdoor venue. It uses weather threat checks and distance-based rules to recommend continuing, suspending, sheltering, or resuming activities.

In plain words
What is it for?
Use it for stadiums, festivals, golf, drone operations, construction, or other outdoor events in the continental United States, with the venue location, event times, and polling interval.
Why use it?
It gives a safety officer consistent decision points while lightning conditions change during an event.

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 →

not rated 0repo 2mo ago A scan 75 tokens original MIT
View source ↗ lostnumber07/shearline
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/event-day-lightning-watch/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 event-day-lightning-watch

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lostnumber07/shearline/event-day-lightning-watch"><img src="https://agentmods.dev/badge/skills/lostnumber07/shearline/event-day-lightning-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 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 $0.00075 $0.00683
Opus 5 $0.00037 $0.00342
Sonnet 5 $0.00015 $0.00137
Haiku 4.5 $0.00007 $0.00068

Measured 10d ago against content hash ce9a42fba5f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

event-day-lightning-watch 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 10d 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/event-day-lightning-watch/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Event-day lightning watch

Goal: keep people safe at a fixed outdoor venue by polling lightning proximity and issuing clear continue / suspend / shelter / resume calls using standard lightning-safety thresholds.

Reminder: this supports an on-site safety officer; it does not replace one. The venue's emergency plan and official warnings take precedence.

Inputs you need

  • Venue — lat, lon (CONUS).
  • Event window — start/end local time.
  • Poll interval — every 5–10 minutes during the window (lightning evolves fast).

Standard thresholds (apply these consistently)

  • ≤ 10 km from the venue → SHELTER NOW (strikes essentially overhead; 30-30 rule).
  • ≤ 16 km (~10 mi) → SUSPEND outdoor activity, move toward shelter.
  • > 16 km but present / approaching → HEIGHTENED WATCH, ready to suspend.
  • Resume only 30 minutes after the last strike within 16 km.

Procedure

  1. Pre-event baseline. get_threat_brief(lat, lon)

    • Note the overall threat_level, the attention_window, and any lightning_summary. If the brief is already elevated+ for storms/lightning, brief the safety officer before doors open.

  2. Poll during the event. Every 5–10 min: get_lightning(lat, lon, radius_km=16, minutes=15)

    • Read data.flash_count, data.flashes_per_min, and data.nearest_strike.distance_km / time_utc.
    • Apply the thresholds above to set the current call.
    • Track the last strike time within 16 km to drive the 30-minute resume clock.

  3. Escalation check. If lightning appears or the flash rate climbs, also run get_threat_brief(lat, lon) to see whether severe weather (not just lightning) is developing — hail/wind/tornado may warrant evacuation beyond a lightning hold.

  4. Resume. When get_lightning shows no strikes within 16 km for a continuous 30 minutes, clear the suspension.

Output template (per poll)

[<time_utc>] Lightning watch — <venue>
Nearest strike: <dist> km <dir> at <time_utc>  (flashes <n>, <rate>/min within 16 km)
CALL: <CONTINUE | HEIGHTENED WATCH | SUSPEND | SHELTER NOW | CLEARED>
Resume eligible at: <last-strike-time + 30 min, or "n/a">
Notes: <e.g. "rate increasing, cell approaching from SW">

Read the full file on GitHub · 56 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. 10d ago First seen · 56 lines · 75 tokens per session scan A ce9a42fba5f0

Subscribe to this mod's changes

event-day-lightning-watch is a skill published in the GitHub repository lostnumber07/shearline (0 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 683 once invoked, about $0.0004 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.

Scientificai-agentsmcpmeteorologymodel-context-protocolmrmsnws
Related

Other skills, from other repositories

cae-postprocess

CAE simulation post-processing translator skill. Translates natural language requests from CFD/FEA/SPH domain experts into viznoir MCP tool calls. Provides domain vocabulary mapping (50+ terms in Korean/English), data-driven visualization idea generation from inspectdata results, and cinematic-first aesthetic guidance…

kimimgo/viznoir · 165 tokens

kernelcad-nurbs

NURBS surfaces (nurbsSurface, surfaceFromCurves, surfaceFromBoundary, .thicken, .toShape) AND NURBS curves (nurbsCurve, spline3d, hermiteG2) AND multi-section sweeps (variableSweep) AND G1/G2 fillet continuity AND 2D NURBS path segments (path().spline / .nurbsSegment / .hermiteG2). Use for freeform geometry that…

w1ne/kernelCAD-web · 105 tokens

fea-workflow

FEA post-processing workflow skill. Guides AI agents through finite element analysis visualization: stress distribution, deformation, mode shapes, and yield detection. Maps FEA domain vocabulary to viznoir MCP tool calls. Triggers: FEA, structural, stress, deformation, displacement, von Mises, yield, mode shape, 응력…

kimimgo/viznoir · 81 tokens

sph-workflow

SPH/DualSPHysics post-processing workflow skill. Guides AI agents through particle method visualization: fluid filtering, sloshing animations, isosurface mesh extraction, and particle distribution analysis. Maps SPH domain vocabulary to viznoir MCP tool calls. Triggers: SPH, DualSPHysics, particles, sloshing, fluid…

kimimgo/viznoir · 91 tokens

kernelcad-trace-from-image

Convert pixel-space features from a reference photo into normalized [0,1] waypoints, then into mm coordinates feedable to path().spline / path().nurbsSegment. Uses the tracefromimage MCP tool. Load when your blockout is in place and the next step is an organic-curve outline (eyewear brow, ergonomic handle, sneaker…

w1ne/kernelCAD-web · 96 tokens

cfd-workflow

CFD post-processing workflow skill. Guides AI agents through computational fluid dynamics visualization: pressure/velocity fields, streamlines, wall shear stress, boundary layers, and pressure drop analysis. Maps CFD domain vocabulary (Korean/English) to viznoir MCP tool calls. Triggers: CFD, flow visualization…

kimimgo/viznoir · 102 tokens