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 gmh5225/awesome-skills --skill platformsgit clone --depth 1 https://github.com/gmh5225/awesome-skillsWrote 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/gmh5225/awesome-skills/platforms)<a href="https://agentmods.dev/skills/gmh5225/awesome-skills/platforms"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-skills/platforms/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/gmh5225/awesome-skills/platforms"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-skills/platforms.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 Agent Snooping · line 71 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00033 | $0.00769 |
| Opus 5.5 | $0.00013 | $0.00308 |
| Sonnet 5.5 | $0.00007 | $0.00154 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
agent-platforms 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 1mo 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Platform Agent Skills
Scope
Use this skill when:
- Ensuring skills work across multiple platforms
- Understanding platform-specific conventions
- Converting skills between platforms
Platform Compatibility Matrix
| Platform | Skill Format | Project Path | Global Path |
|---|---|---|---|
| Amp | SKILL.md | .agents/skills/ |
~/.config/agents/skills/ |
| Antigravity | SKILL.md | .agent/skills/ |
~/.gemini/antigravity/skills/ |
| Claude Code | SKILL.md | .claude/skills/ |
~/.claude/skills/ |
| Codex | SKILL.md | .codex/skills/ |
~/.codex/skills/ |
| Cursor | SKILL.md | .cursor/skills/ |
~/.cursor/skills/ |
| Gemini CLI | SKILL.md | .gemini/skills/ |
~/.gemini/skills/ |
| GitHub Copilot | SKILL.md | .github/skills/ |
~/.copilot/skills/ |
| Goose | SKILL.md | .goose/skills/ |
~/.config/goose/skills/ |
| OpenCode | SKILL.md | .opencode/skills/ |
~/.config/opencode/skills/ |
| Windsurf | SKILL.md | .windsurf/skills/ |
~/.codeium/windsurf/skills/ |
Universal SKILL.md Format
All platforms use YAML frontmatter:
---
name: skill-name
description: When to use this skill
---
# Instructions here...
Cross-Platform Installation
Most tools auto-discover skills in .agent/skills/:
# Universal installation (works with most tools)
git clone https://github.com/user/skills .agent/skills
Platform-Specific Notes
Claude Code
- Auto-discovers from
.claude/skills/and~/.claude/skills/ - Supports
/initcommand for context bootstrapping
Codex (OpenAI)
- Supports multiple scopes: REPO, USER, ADMIN, SYSTEM
- Built-in
$skill-creatorand$skill-installer - Restart required after installing new skills
GitHub Copilot
- Skills in
.github/skills/directory - Uses
SKILL.mdwithnameanddescriptionrequired - Copilot auto-activates based on description match
Gemini CLI
- Use
@symbol to attach skill files to prompts - Place skills in
.gemini/skills/or.agent/skills/
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.
- 1mo ago First seen · 89 lines · 33 tokens per session scan A 7e2d71824911
agent-platforms is a skill published in the GitHub repository gmh5225/awesome-skills (97 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 769 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 2026-08-30.
Other skills, from other repositories
api-to-example
Turns REST API documentation into a runnable curl, fetch, or code example with required headers, request body, and placeholders for secrets. Use when the user wants to generate a request from API docs, an endpoint, or a Swagger/OpenAPI spec — "give me a curl for this", "show a fetch example", "how do I call this API".
code-translator
Converts a code snippet from one programming language to another while preserving behavior and flagging library, runtime, and type-system differences. Use when the user asks to translate, port, rewrite, or convert code between languages — "port this to Python", "rewrite in Rust", "convert Java to Go".
libretranslate-markdown-i18n
Machine-translate Markdown / Obsidian / Quartz content into other languages using a self-hosted LibreTranslate instance, preserving frontmatter, headings, emojis, bold/italic, wikilinks (![[...]]/[[...]]) and internal links. Use whenever a user wants to auto-translate a Markdown vault, Obsidian notes, or a…
animated-portfolio-sites
Build a one-page animated personal or portfolio site (canvas starfield, rotating galaxies with mouse parallax, hidden accordion/card content, anchor nav) and publish it free on GitHub Pages. Covers the canvas technique and the Pages permission wall, not just one task.
deal-checker
Judges whether a product's price is worth it by checking typical prices, alternatives, total cost, and timing, then giving a clear buy / wait / skip call. Use when the user asks "is this a good deal", "should I buy this", "is this worth the price", "too expensive", or wants a price check or comparison before…
job-fit-review
Reviews a job posting or pasted job description for fit, gaps, legitimacy signals, compensation context, resume customization, and interview prep. Use when the user shares a job posting, job listing, job ad, or job description and wants help deciding whether to apply, evaluating the role, or checking if a job is legit.