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.
git clone --depth 1 https://github.com/gami34/antigravity-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/plugins/gami34/antigravity-awesome-skills/antigravity-awesome-skills-claude)<a href="https://agentmods.dev/plugins/gami34/antigravity-awesome-skills/antigravity-awesome-skills-claude"><img src="https://agentmods.dev/badge/plugins/gami34/antigravity-awesome-skills/antigravity-awesome-skills-claude/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/plugins/gami34/antigravity-awesome-skills/antigravity-awesome-skills-claude"><img src="https://agentmods.dev/badge/plugins/gami34/antigravity-awesome-skills/antigravity-awesome-skills-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
antigravity-awesome-skills 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 12d 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.
This is a copy
91% identical to antigravity-awesome-skills — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "antigravity-awesome-skills",
"version": "11.11.0",
"description": "Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,465 supported skills.",
"author": {
"name": "sickn33 and contributors",
"url": "https://github.com/sickn33/antigravity-awesome-skills"
},
"homepage": "https://github.com/sickn33/antigravity-awesome-skills",
"repository": "https://github.com/sickn33/antigravity-awesome-skills",
"license": "MIT",
"keywords": [
"claude-code",
"skills",
"agentic-skills",
"plugin-safe",
"productivity"
]
}
What it installs
The manifest is a name and a version. 57 skills travel with it, and installing the plugin installs all of them — 2,308 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ai-engineering-toolkit A 47 tokens
- Skill algorithmic-art A 43 tokens
- Skill 007 A 39 tokens
- Skill agent-framework-azure-ai-py A 24 tokens
- Skill agents-md A 62 tokens
- Skill ai-wrapper-product A 47 tokens
- Skill advogado-criminal A 42 tokens
- Skill advogado-especialista A 38 tokens
- Skill agentphone A 57 tokens
- Skill ai-seo A 47 tokens
- Skill alpha-vantage A 34 tokens
- Skill ad-creative A 51 tokens
- Skill agent-orchestration-improve-agent A 25 tokens
- Skill agents-v2-py A 39 tokens
- Skill 3d-web-experience A 57 tokens
- Skill advanced-evaluation A 59 tokens
- Skill agent-orchestration-multi-agent-optimize A 38 tokens
- Skill agentic-actions-auditor A 63 tokens
- Skill ai-analyzer A 46 tokens
- Skill amazon-alexa A 53 tokens
- Skill analytics-tracking A 21 tokens
- Skill agent-manager-skill A 28 tokens
- Skill ai-native-cli A 44 tokens
- Skill agent-orchestrator A 41 tokens
- Skill ai-studio-image A 38 tokens
- Skill activecampaign-automation A 41 tokens
- Skill agentflow A 52 tokens
- Skill agentmail A 31 tokens
- Skill amplitude-automation A 37 tokens
- Skill analytics-product A 35 tokens
- Skill aegisops-ai A 41 tokens
- Skill agenttrace-session-audit A 34 tokens
- Skill ai-dev-jobs-mcp A 41 tokens
- Skill ai-ml A 30 tokens
- Skill address-github-comments A 27 tokens
- Skill adhx A 49 tokens
- Skill ai-agent-development A 32 tokens
- Skill active-directory-attacks B 42 tokens
- Skill agent-memory-mcp A 26 tokens
- Skill akf-trust-metadata A 60 tokens
- Skill ab-test-setup A 25 tokens
- Skill agent-tool-builder A 57 tokens
- Skill agent-memory-systems A 51 tokens
- Skill ai-engineer A 37 tokens
- Skill 10-andruia-skill-smith A 45 tokens
- Skill algolia-search A 22 tokens
- Skill ai-agents-architect A 31 tokens
- Skill airtable-automation A 37 tokens
- Skill agentfolio A 23 tokens
- Skill 00-andruia-consultant A 45 tokens
- Skill 20-andruia-niche-intelligence A 56 tokens
- Skill acceptance-orchestrator A 37 tokens
- Skill accessibility-compliance-accessibility-audit A 40 tokens
- Skill agent-evaluation B 38 tokens
- Skill airflow-dag-patterns A 42 tokens
- Skill ai-md B 33 tokens
- Skill ai-product C 28 tokens
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.
- 12d ago First seen · 20 lines scan A d5ae3c8e85f7
antigravity-awesome-skills is a plugin published in the GitHub repository gami34/antigravity-awesome-skills (1 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 91% identical to antigravity-awesome-skills, differing in 4 lines, and is treated as a copy.
Other plugins, from other repositories
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
knowledge-work-plugins marketplace
Plugin marketplace listing 104 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.