A command-line tool for reading hyper-local weather from a WeatherFlow Tempest weather station. It can use the station's REST API or the hub's local network broadcast for current, forecast, historical, and real-time readings.

It is for querying conditions, forecasts, and history, and decoding live observations such as wind, rain, lightning, and hub status.

It lets an agent retrieve station data without relying only on a weather website or graphical app.

tempest — Skill for Claude Code and Codex by magnus919

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add magnus919/agent-skills --skill tempest

Clone the repo

git clone --depth 1 https://github.com/magnus919/agent-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin tempest — /plugin install tempest after adding the marketplace above.

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/magnus919/agent-skills/tempest/github.svg)](https://agentmods.dev/skills/magnus919/agent-skills/tempest)

Your own site

<a href="https://agentmods.dev/skills/magnus919/agent-skills/tempest"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/tempest/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/magnus919/agent-skills/tempest"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/tempest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,335 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 39
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
medium Rogue Agent · line 18
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.

How audits are shown

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	$0.00166	$0.03335
Opus 5	$0.00083	$0.01667
Sonnet 5	$0.00033	$0.00667
Haiku 4.5	$0.00017	$0.00333

Measured 9d ago against content hash c47f05d341b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tempest 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/test_tempest.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

tempest/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tempest — Hyper-local weather from your Tempest station

Drive a WeatherFlow Tempest station from the terminal. Two transports, both first-class: the documented REST API (swd.weatherflow.com/swd/rest, personal-use token) for conditions, forecast, and history — officially the primary data source — and the hub's unauthenticated UDP broadcast on port 50222 for real-time, lowest-latency readings on your LAN. The bundled CLI decodes the positional observation arrays and every UDP message family, keeps --json output metric-native, and converts units only for human display.

Setup

Create a personal access token: sign in to the Tempest web app (tempestwx.com), then Settings → Data Authorizations → Create Token. (This is the documented non-graphical auth method; OAuth exists for web apps but is not what a CLI uses.)
Export it:

export TEMPEST_TOKEN="<YOUR_TOKEN>"

The token travels to the API as a query parameter (?token=...) per the official docs — the CLI handles this. If the env var is not set, the CLI falls back to reading TEMPEST_TOKEN= from ~/.tempest.env (handy for agent subprocesses that skip shell profiles). --help and --dry-run never need a token. UDP listening never needs one either — the hub broadcast is unauthenticated and LAN-only.

Essential Commands

stations — discover your stations and devices

tempest stations                       # names, station ids, device types, serials
tempest stations --json | jq '.stations[] | {station_id, name,
  devices: [.devices[] | {device_id, device_type, serial_number}]}'

Every station response nests a devices array: device_type is ST (the Tempest all-in-one), AR/AIR, SK/SKY, or HB (the hub — it has no observations; always filter it out before querying observations). Run this first when you don't know your ids.

current — latest conditions

tempest current                                       # human-readable, converted
tempest current --json                                # metric-native, jq-ready
tempest current --station-id 12799 --device-id 60526  # pin exact hardware

Read the full file on GitHub · 277 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 277 lines · 166 tokens per session scan A c47f05d341b8

Subscribe to this mod's changes

tempest is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 166 tokens to every session and 3,335 once invoked, about $0.0008 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 2026-09-03.

Hardware and IoT LLM agent-skills agentskills ai-agents automation

rosclaw-embodied

A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.

ros-claw/rosclaw · 54 tokens

modem-tune

Change the reported IMEI on a configured GL.iNet travel router (GL-XE300 or GL-E5800, auto-detected) for work testing. Generates a fresh, never-reused device-class IMEI locally (TAC from per-device config), connects to the modem over SSH, records the outgoing IMEI with a timestamp, applies the change, confirms the…

mishahanin/heading-os · 151 tokens

findmypipe

Locate Apple devices (iPhone, iPad, Mac, AirPods) via iCloud Find My using the findmy-agent CLI. Use this skill when the user asks to find an Apple device, check iPhone/iPad/Mac/AirPods location, locate lost AirPods, "Where's my iPhone", "Dov'è il mio Mac", verify if a device is home vs away, or check if devices are…

corryl/FindMyPipe · 105 tokens

tempest