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.
npx skills add runxhq/runx --skill open-meteo-weathergit clone --depth 1 https://github.com/runxhq/runxWrote 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.
[](https://agentmods.dev/skills/runxhq/runx/open-meteo-weather)<a href="https://agentmods.dev/skills/runxhq/runx/open-meteo-weather"><img src="https://agentmods.dev/badge/skills/runxhq/runx/open-meteo-weather/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.
<a href="https://agentmods.dev/skills/runxhq/runx/open-meteo-weather"><img src="https://agentmods.dev/badge/skills/runxhq/runx/open-meteo-weather.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00029 | $0.01069 |
| Opus 5.5 | $0.00012 | $0.00428 |
| Sonnet 5.5 | $0.00006 | $0.00214 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
open-meteo-weather 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open-Meteo Weather
Fetch global place, forecast, and air-quality evidence through runx's governed
connector boundary. The skill never performs an ad-hoc fetch. Each provider stage is a bounded,
read-only HTTP runner whose endpoint, inputs, status, authority scope, and
output packet are recorded in the sealed receipt. The built-in connector uses
public keyless endpoints. Commercial use needs an appropriate Open-Meteo plan
and connector; keyless access is not a commercial entitlement. This is the worldwide counterpart to the US-only
nws-weather provider.
Procedure
- Run the default
weatherrunner withnameand any regionallocation_context. It reads the geocoder once and asks the operating agent to select an actual returned candidate, or preserve unresolved ambiguity. - A bounded domain function binds that candidate id to the original provider
record before any weather request. The record and native geocoding readback
remain in
location; request coordinates use six decimal places to match the existing connector input contract. - Read the requested
kind:forecast(default) orair_quality. Already resolved coordinates use the explicitforecastorair_qualityrunner, bypassing geocoding and selection entirely. - Require a 2xx response and preserve the provider URL, timezone, generation time, current conditions, daily forecast, and receipt references.
- Treat the result as context only. Any notification, scheduling change, or operational mutation requires a separate skill and authority gate.
Inputs
name(weatherandlocate, required): city or place to resolve.location_context(weather, optional): country, administrative area or other intent.kind(weather, optional):forecastorair_quality, defaultforecast.latitude(forecast, required): decimal latitude.longitude(forecast, required): decimal longitude.forecast_days(forecast, optional): days requested, default3.
What ships with it
12 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.
- fixtures/composes-in-graph.yaml 833 B
- fixtures/open-meteo-air-quality-shanghai.yaml 956 B
- fixtures/open-meteo-shanghai.yaml 2.3 KB
- fixtures/place-air-quality.yaml 2.6 KB
- fixtures/place-ambiguous.yaml 1.6 KB
- fixtures/place-forecast.yaml 2.8 KB
- fixtures/place-invented-id.yaml 1.4 KB
- fixtures/place-no-match.yaml 1.2 KB
- fixtures/support/composed.graph 243 B
- location.mjs 1.3 KB runs code
- references/catalog.md 147 B
- run.yaml 5.7 KB
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.
- yesterday Changed · +29 lines 7fe58ff0c265
- 20d ago First seen · 71 lines · 29 tokens per session scan A 3adb1b80202c
open-meteo-weather is a skill published in the GitHub repository runxhq/runx (104 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 1,069 once invoked, about $0.0001 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 2026-10-18.
open-meteo-weather compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| open-meteo-weatherrunxhq/runx | Skill | 104 | yesterday | Apache-2.0 | A | 29 | Claude Code, Codex |
| dd-synthesisAbilityai/trinity | Skill | 741 | yesterday | Apache-2.0 | A | 33 | Claude Code, Codex |
| dd-report-formatAbilityai/trinity | Skill | 741 | yesterday | Apache-2.0 | A | 27 | Claude Code, Codex |
| dd-risk-scoringAbilityai/trinity | Skill | 741 | yesterday | Apache-2.0 | A | 29 | Claude Code, Codex |
| dd-sourcingAbilityai/trinity | Skill | 741 | yesterday | Apache-2.0 | A | 29 | Claude Code, Codex |
| dd-verificationAbilityai/trinity | Skill | 741 | yesterday | Apache-2.0 | A | 35 | Claude Code, Codex |
| sagemath02loveslollipop/OpenCROW | Skill | 10 | yesterday | Apache-2.0 | A | 68 | Claude Code, Codex |