What is chase-day-briefing?

A procedure for producing a same-day severe-weather briefing for a location in the continental United States. It combines outlooks, current atmospheric conditions, trends, warnings, and radar into a go, hold, or no-go decision.

Use it to plan storm chasing, assess outdoor-operation risk, and identify the most concerning time window, while treating official National Weather Service warnings as the life-safety authority.

It organizes changing weather information into a short field-safety decision for storm chasers, emergency managers, or outdoor teams.

How lostnumber07/shearline configures Claude Code

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/chase-day-briefing/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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lostnumber07/shearline/chase-day-briefing/github.svg)](https://agentmods.dev/skills/lostnumber07/shearline/chase-day-briefing)

Your own site

<a href="https://agentmods.dev/skills/lostnumber07/shearline/chase-day-briefing"><img src="https://agentmods.dev/badge/skills/lostnumber07/shearline/chase-day-briefing/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lostnumber07/shearline/chase-day-briefing"><img src="https://agentmods.dev/badge/skills/lostnumber07/shearline/chase-day-briefing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 753 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.

Model	Per session	Once invoked
Fable 5.1	$0.00069	$0.00753
Opus 5.5	$0.00028	$0.00301
Sonnet 5.5	$0.00014	$0.00151
Haiku 4.5	$0.00007	$0.00075

Measured 2mo ago against content hash 6b84835a66d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chase-day-briefing 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.

.claude/skills/chase-day-briefing/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chase-day briefing

Goal: a concise field briefing for a target point today — what's expected, is the environment loaded and trending up, is anything already happening, and a clear go / hold / no-go with the window of greatest concern.

Reminder: SHEARLINE is decision support. Official NWS watches/warnings drive life-safety decisions; say so in the briefing.

Inputs you need

Target — lat, lon (CONUS). For a region, pick the centroid or run the sequence for two or three candidate points.

Procedure (run in this order; the later steps refine the earlier)

The forecast frame. get_spc_outlook(lat, lon, day=1)
- Note data.categorical.label (MRGL→HIGH) and the tornado/hail/wind probabilities. If you're planning ahead, also day=2.
The environment now. get_point_environment(lat, lon)
- Read the interpretation — it names the regime (pulse / cool-season high-shear / classic supercell). Note MLCAPE, 0–6 km shear, 0–1 km SRH, SCP, effective STP, and whether instability is capped (large negative MLCIN matters — storms may not fire until the cap erodes).
The trajectory. get_environment_trend(lat, lon)
- This is the chase-critical step: is STP/CAPE rising into the afternoon, or stabilizing? Read the trend interpretation ("intensifying" vs "weakening").
What's already up. get_active_warnings(lat, lon, radius_km=80) and get_mrms_severe(lat, lon, radius_km=80)
- Any active warnings, and any MESH / rotation-track signatures already in range (storms upstream that will move toward the target).
Synthesize. Optionally run get_threat_brief(lat, lon) for the composite level, then write the call.

Output template

Chase briefing — (<lat>, <lon>), <date>
Outlook: SPC <category>; tornado <x>% / hail <y>% / wind <z>%
Environment: <regime in one phrase>; MLCAPE <..> J/kg, 0-6km shear <..> kt,
             0-1km SRH <..>, eff-STP <..>, SCP <..>; cap: <none/weak/strong>
Trend (f00→f06): <intensifying | steady | weakening> — <one line>
Already active: <warnings / MESH / rotation in range, or "nothing yet">
CALL: <GO | HOLD | NO-GO>
Target window: <e.g. 21–01Z as heating maximizes / cap erodes>
Watch for: <the single signal that would change the call, e.g.
            "rotation track appearing within 60 km to the SW">
Safety: follow live NWS warnings; this is planning support only.

Read the full file on GitHub · 58 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.

2mo ago First seen · 58 lines · 69 tokens per session scan A 6b84835a66d2

Subscribe to this mod's changes

chase-day-briefing is a skill published in the GitHub repository lostnumber07/shearline (1 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 753 once invoked, about $0.0003 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.

Scientific

chase-day-briefing next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chase-day-briefinglostnumber07/shearline	Skill	1	1mo ago	MIT	A	69	Claude Code
instrument-data-to-allotropeanthropics/knowledge-work-plugins	Skill	35k	2d ago	Apache-2.0	A	123	Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	83	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	44	Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	A	71	Claude Code, Codex
research-engineerdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	43	Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmed	Skill	5.8k	yesterday	Apache-2.0	A	205	Claude Code

shearline: Skill for Claude Code