PicoClaw is a lightweight personal AI assistant written in Go and designed to run on compact, resource-constrained hardware. People use it as a deployable assistant for automating everyday tasks, with development still in an early stage. The catalogue skills extend how coding agents work with PicoClaw.
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 sipeed/picoclaw --skill weathergit clone --depth 1 https://github.com/sipeed/picoclawWrote 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/sipeed/picoclaw/weather)<a href="https://agentmods.dev/skills/sipeed/picoclaw/weather"><img src="https://agentmods.dev/badge/skills/sipeed/picoclaw/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/sipeed/picoclaw/weather"><img src="https://agentmods.dev/badge/skills/sipeed/picoclaw/weather.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Data Exfiltration · line 52 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00017 | $0.00726 |
| Opus 5.5 | $0.00007 | $0.00290 |
| Sonnet 5.5 | $0.00003 | $0.00145 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
weather scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
metadata: {"nanobot":{"emoji":"🌤️","requires":{"bins":["curl"]}}} How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weather
Use the most reliable location match first. For Chinese city names or other non-Latin input, prefer wttr.in with the original query because it resolves native names directly. Use Open-Meteo for structured current conditions and forecasts only after you have confirmed the exact city.
Accuracy Rules
- Always restate the matched location, region/country, and observation time in the final answer.
- Do not trust the first geocoding hit blindly. Check
country,admin1,admin2, andpopulation. - For Chinese city queries, do not send Hanzi directly to Open-Meteo geocoding unless the top result is obviously correct. Prefer
wttr.inwith the original Chinese name, or geocode the English/pinyin city name instead. - If multiple plausible matches remain, ask a follow-up question or state the assumption clearly.
- Use
timezone=autowhen calling Open-Meteo so the reported time matches the location.
wttr.in (best for direct city-name queries)
Quick current conditions:
curl -s "https://wttr.in/London?format=%l:+%c+%t+%h+%w"
Chinese city example:
curl -s "https://wttr.in/%E6%88%90%E9%83%BD?format=%l:+%c+%t+%h+%w"
curl -s "https://wttr.in/%E4%B8%8A%E6%B5%B7?format=%l:+%c+%t+%h+%w"
JSON output if you need more detail:
curl -s "https://wttr.in/Chengdu?format=j1"
Tips:
- URL-encode spaces:
New York->New+York - URL-encode non-ASCII text before sending the request
- Use
?mfor metric units and?ufor US units
Open-Meteo (best for structured forecasts)
- Geocode the city and verify the returned location metadata:
curl -s "https://geocoding-api.open-meteo.com/v1/search?name=Chengdu&count=3&language=en&format=json"
- Query current weather and today's forecast with the verified coordinates:
curl -s "https://api.open-meteo.com/v1/forecast?latitude=30.66667&longitude=104.06667¤t=temperature_2m,relative_humidity_2m,weather_code,wind_speed_10m&daily=weather_code,temperature_2m_max,temperature_2m_min&forecast_days=1&timezone=auto"
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 · 60 lines · 17 tokens per session scan A 416c125afb7d
weather is a skill published in the GitHub repository sipeed/picoclaw (30,103 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 726 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
weather compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| weathersipeed/picoclaw | Skill | 30k | yesterday | MIT | A | 17 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |