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.
/plugin marketplace add agentskill-sh/agsnpx agentmods add plugins/agentskill-sh/ags/marketplacegit clone --depth 1 https://github.com/agentskill-sh/agsGrade A, and why
agentskill-sh 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 2d 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.
What it actually says
{
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
"name": "agentskill-sh",
"description": "Skills from agentskill.sh — the AI agent skills directory. Install the /learn command to discover, install, and manage skills for Claude Code, Cursor, Copilot, and other AI agents.",
"owner": {
"name": "agentskill.sh",
"email": "[email protected]"
},
"metadata": {
"version": "1.0.0"
},
"plugins": [
{
"name": "learn",
"source": "skills/learn",
"description": "Helps users discover and install agent skills when they ask questions like \"how do I do X\", \"find a skill for X\", \"is there a skill that can...\", or express interest in extending capabilities. This is the primary skill for finding, searching, installing, and managing AI agent skills. Use /learn to search 100,000+ skills from agentskill.sh, install them mid-session, track versions, and rate skills after use. This skill should be used when the user is looking for functionality that might exist as an installable skill.",
"version": "1.0.0",
"author": {
"name": "agentskill.sh",
"url": "https://agentskill.sh"
},
"homepage": "https://agentskill.sh/install",
"repository": "https://github.com/agentskill-sh/ags",
"license": "MIT",
"keywords": ["skills", "learn", "install", "agent", "directory"],
"category": "productivity",
"tags": ["skills", "marketplace", "discovery"]
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 31 lines scan A 018b93dff704
agentskill-sh is a plugin published in the GitHub repository agentskill-sh/ags (35 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
wt-local
Local marketplace populated by wta.
agentlas-core-engine
Plugin marketplace listing 1 plugin: hephaestus.
lattice
A marketplace of composable AI skills covering the full software delivery lifecycle — from requirements and design through implementation, testing, and review. Each plugin targets a specific SDLC role: backend engineers, frontend engineers, QA, business analysts, and more.
fw-app-dev
Expert-level skill for building, debugging, reviewing, and migrating Freshworks Platform 3.0 custom apps.
fw-setup
Install, upgrade, downgrade, and uninstall the Freshworks Development Kit (FDK) with Node.js via nvm (macOS, Windows, Linux).
engineering
Streamline engineering workflows — standups, code review, architecture decisions, incident response, and technical documentation. Works with your existing tools or standalone.