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 agentmods add plugins/tradecatlabs/fatecat/marketplace/plugin marketplace add tradecatlabs/fatecatgit clone --depth 1 https://github.com/tradecatlabs/fatecatGrade A, and why
master-skill 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 yesterday.
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
{
"name": "master-skill",
"description": "Buddhist Master AI Skills — 14 historical masters across 汉传/藏传/南传 plus 3 teaching meta-skills (compare / debate / curriculum), with source-cited teachings",
"owner": {
"name": "xr843",
"email": "[email protected]"
},
"plugins": [
{
"name": "master-skill",
"description": "Buddhist Master AI teaching personas — 14 prebuilt masters across 汉传/藏传/南传 plus 3 teaching meta-skills (compare-masters / master-debate / master-curriculum), invokable via /master-<slug> slash commands, with source-cited doctrinal responses (CBETA / BDRC / SuttaCentral / PTS Vism), RAG-grounded in FoJin knowledge graph",
"version": "0.9.1",
"source": "./",
"author": {
"name": "xr843",
"email": "[email protected]"
}
}
]
}
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.
- yesterday First seen · 21 lines scan A 555486ccfda6
master-skill is a plugin published in the GitHub repository tradecatlabs/fatecat (203 stars, last pushed 6d 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
geo-tool
Free GEO tools by geo-tool.com: check whether pages are readable and citable for AI search (ChatGPT, Perplexity, Claude, Google AI).
geo-tool-check
AI search readiness checks (GEO): score any public page 0-100, see which AI crawlers robots.txt blocks, and score draft passages for citability. Same engine as geo-tool.com, runs locally, no account.
afterlaunch-growth
Growth marketing, SEO and AI answer-engine visibility (GEO) for a product, run through AfterLaunch over MCP. Bundles the AfterLaunch remote MCP server and a skill that teaches an agent to read the ranked Feed and ship prepared growth moves instead of improvising.
workhours
Track worked hours by client, project and task straight from Claude Code. Ships the workhours MCP server (Docker image, no build needed) and a skill teaching the model how to use it.
edulab
教育类技能集合：把学科问题转成可交互的教学网页。edu-solid-geometry 立体几何解题（建系+向量法，3D Three.js + MathJax）；edu-analytic-geometry 解析几何/圆锥曲线解题（sympy 精确计算 + 实时交互 2D 画板 + KaTeX）；edu-chem-reaction 化学反应微观 3D 演示（sympy 自动配平 + 原子守恒，morph/mechanism 双引擎，Three.js + KaTeX）。.
Master-skill
FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready. 15 prebuilt masters across 印度/汉传/藏传/南传 plus compare, debate, and curriculum meta-skills.