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 agentmods add skills/vironnimo/vbot/weathernpx skills add Vironnimo/vbot --skill weathergit clone --depth 1 https://github.com/Vironnimo/vbotWhat 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 | $0.00109 | $0.00862 |
| Opus 5 | $0.00055 | $0.00431 |
| Sonnet 5 | $0.00022 | $0.00172 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weather
Use this for current conditions, rain and temperature checks, and short-range forecasts — for a city, region, airport code, landmark, or coordinates. You always need a location: if the user gives none and none is clear from context, ask for one.
How to fetch it
Fetch weather with the web_fetch tool against wttr.in, a free service that needs no API key. Always request the JSON format j2:
web_fetch(url: "https://wttr.in/London?format=j2")
Request format=j2 on purpose. web_fetch sends browser-like headers, so for wttr.in's human-readable formats the service answers with decorative HTML/ANSI that is useless to parse. j2 returns compact JSON instead — current conditions plus a 3-day forecast, without the bulky per-hour data — which web_fetch hands back verbatim (a few KB, well within its output cap). Parse that JSON and summarize it; do not read the weather back field by field.
Building the URL
The location goes in the URL path. Encode spaces as +:
- City or region —
https://wttr.in/Berlin?format=j2,https://wttr.in/New+York?format=j2 - Airport code —
https://wttr.in/MUC?format=j2 - Coordinates —
https://wttr.in/48.85,2.35?format=j2 - Landmark or point of interest — prefix with
~:https://wttr.in/~Eiffel+Tower?format=j2
Reading the JSON
Summarize current_condition[0], nearest_area[0] (to confirm the resolved place), and the first entries of weather[] for the forecast. wttr.in returns both metric and imperial fields — pick the units that fit the user.
Current conditions — current_condition[0]:
weatherDesc[0].value— condition text (e.g. "Partly cloudy")temp_C/temp_F— temperatureFeelsLikeC/FeelsLikeF— feels-like temperatureprecipMM— precipitationhumidity— relative humidity (%)windspeedKmph/windspeedMiles— wind speed
Forecast — each entry in weather[] (today plus the next days):
datemintempC/maxtempC(and the…Fvariants)avgtempC,uvIndex, andastronomy[0]for sunrise / sunset
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 First seen · 54 lines · 109 tokens per session scan A 7c00ce806d8b
weather is a skill published in the GitHub repository Vironnimo/vbot (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 109 tokens to every session and 862 once invoked, about $0.0005 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.
Other skills, from other repositories
gpt-researcher
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations. Use this skill when helping developers understand, extend, debug, or integrate with GPT Researcher - including adding features, understanding the architecture, working with the API…
review-pr
Review a Dograh pull request, branch diff, or pasted patch for repo-specific security and correctness risks that are not obvious from generic FastAPI, Next.js, or Python conventions. Use when the user asks to review a PR, audit a diff, check whether changes are safe to merge, review their own changes, or asks what to…
review-agents-md
Audit Dograh AGENTS.md files for drift against the live repo and for bad scope boundaries between parent and child docs. Use when the user asks to review existing AGENTS files, identify stale guidance, decide whether a subtree needs its own AGENTS.md, or update the AGENTS.md hierarchy under the repo root, api/, or ui/.
merge-pipecat-upstream
Merge the latest upstream pipecat-ai/pipecat tag into the pipecat submodule fork (dograh-hq/pipecat) and bump the dograh repo to it. Use whenever the user asks to bump, upgrade, sync, or merge pipecat, resolve pipecat merge conflicts, audit whether upstream changes break or supersede Dograh's in-fork patches, or…
gpt-researcher
Autonomous deep research from Codex via MCP.
quantdinger-agent-workflow
QuantDinger repo workflow for coding agents: layered contracts, safety boundaries, and where backend, strategies, and Docker live. Use when editing Python API, strategies, deployment, or docs/agent.