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 joeynyc/skillscore --skill test-skillgit clone --depth 1 https://github.com/joeynyc/skillscoreWrote 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/joeynyc/skillscore/test-skill)<a href="https://agentmods.dev/skills/joeynyc/skillscore/test-skill"><img src="https://agentmods.dev/badge/skills/joeynyc/skillscore/test-skill/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/joeynyc/skillscore/test-skill"><img src="https://agentmods.dev/badge/skills/joeynyc/skillscore/test-skill.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 | $0.00000 | $0.00400 |
| Opus 5.5 | $0.00000 | $0.00160 |
| Sonnet 5.5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
test-skill scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl or wget for HTTP requests What it actually says
Weather Information Fetcher
Fetches current weather data for any city using OpenWeatherMap API.
Dependencies
- curl or wget for HTTP requests
- OpenWeatherMap API key (free registration at openweathermap.org)
- Environment variable: OPENWEATHER_API_KEY
Installation
- Sign up for API key at https://openweathermap.org/api
- Set environment variable:
export OPENWEATHER_API_KEY=your_api_key - Ensure curl is installed:
which curl
Usage
- When user asks for weather information for a specific city
- Extract the city name from the request
- Make API call:
curl "http://api.openweathermap.org/data/2.5/weather?q=CITY&appid=$OPENWEATHER_API_KEY&units=metric" - Parse the JSON response and format for user
- Handle errors gracefully if city not found or API unavailable
Examples
# Example API call
curl "http://api.openweathermap.org/data/2.5/weather?q=London&appid=your_api_key&units=metric"
Expected response includes temperature, description, humidity, and pressure.
Error Handling
- No API key: Prompt user to set OPENWEATHER_API_KEY environment variable
- City not found: Return "City not found, please check spelling"
- API down: Fallback to generic message "Weather service temporarily unavailable"
- Network error: Retry once, then inform user of connection issue
Limitations
- Requires internet connection
- API has rate limits (1000 calls/day for free tier)
- Only supports current weather (not forecasts)
- City names must be in English
Troubleshooting
If you get "unauthorized" error:
- Verify API key is correct
- Check if key is activated (can take up to 10 minutes)
- Ensure environment variable is set properly
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 · 53 lines · 0 tokens per session scan A 9e5e399c1ce5
test-skill is a skill published in the GitHub repository joeynyc/skillscore (18 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 400 tokens. 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.
test-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| test-skilljoeynyc/skillscore | Skill | 18 | 6mo ago | MIT | A | 0 | Claude Code, Codex |
| officecli-pitch-deckiOfficeAI/OfficeCLI | Skill | 33k | yesterday | Apache-2.0 | A | 163 | Claude Code, Codex |
| morph-pptiOfficeAI/OfficeCLI | Skill | 33k | yesterday | Apache-2.0 | A | 169 | Claude Code, Codex |
| officecli-academic-paperiOfficeAI/OfficeCLI | Skill | 33k | yesterday | Apache-2.0 | A | 141 | Claude Code, Codex |
| officecli-financial-modeliOfficeAI/OfficeCLI | Skill | 33k | yesterday | Apache-2.0 | A | 222 | Claude Code, Codex |
| officecli-pptxiOfficeAI/OfficeCLI | Skill | 33k | yesterday | Apache-2.0 | A | 106 | Claude Code, Codex |
| officecliiOfficeAI/OfficeCLI | Skill | 33k | yesterday | Apache-2.0 | A | 56 | Claude Code, Codex |