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/frank-luongt/faos-skills-marketplaceWrote 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/frank-luongt/faos-skills-marketplace/faos-analyst)<a href="https://agentmods.dev/plugins/frank-luongt/faos-skills-marketplace/faos-analyst"><img src="https://agentmods.dev/badge/plugins/frank-luongt/faos-skills-marketplace/faos-analyst/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80ร15 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/frank-luongt/faos-skills-marketplace/faos-analyst"><img src="https://agentmods.dev/badge/plugins/frank-luongt/faos-skills-marketplace/faos-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
faos-analyst scanned grade A with 0 findings against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ measured 13d 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
{
"_generated_by": "export-plugins.py",
"name": "faos-analyst",
"version": "1.0.0",
"description": "๐ Business Analyst โ Strategic Business Analyst + Requirements Expert",
"author": {
"name": "FAOS Framework",
"url": "https://github.com/frank-luongt/Foundation-AgenticOS"
},
"repository": "https://github.com/frank-luongt/Foundation-AgenticOS",
"license": "Apache-2.0",
"keywords": [
"faos",
"analyst",
"product",
"bmm"
]
}
What it installs
The manifest is a name and a version. 22 skills, 6 commands travel with it, and installing the plugin installs all of them โ 0 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill app-store-optimization A 0 tokens
- Skill campaign-analytics A 0 tokens
- Skill enterprise-search A 0 tokens
- Skill hr-operations A 0 tokens
- Skill customer-success-playbook A 0 tokens
- Skill finance-accounting A 0 tokens
- Skill opportunity-solution-tree A 0 tokens
- Skill revenue-operations A 0 tokens
- Skill ab-test-analysis A 0 tokens
- Skill interview-script A 0 tokens
- Skill legal-contract-review A 0 tokens
- Skill marketing-psychology A 0 tokens
- Skill pricing-strategy A 0 tokens
- Skill summarize-interview A 0 tokens
- Skill cxo-thinkos A 0 tokens
- Skill page-cro A 0 tokens
- Skill seo-audit A 0 tokens
- Skill analytics-tracking A 0 tokens
- Skill market-sizing-analysis A 0 tokens
- Skill brainstorming A 0 tokens
- Skill ab-test-setup A 0 tokens
- Skill business-analyst A 0 tokens
- Command deep-research A 0 tokens
- Command document-project A 0 tokens
- Command quick-research A 0 tokens
- Command research A 0 tokens
- Command brainstorm-project A 0 tokens
- Command product-brief A 0 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.
- 13d ago First seen ยท 19 lines scan A 588e5b97f9d0
faos-analyst is a plugin published in the GitHub repository frank-luongt/faos-skills-marketplace (33 stars, last pushed 2mo ago), licensed Apache-2.0. 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
job-hunt-skills
Tailor resumes, cover letters, and interview prep to specific roles and organize your job search. Covers research, applications, interviews, LinkedIn, and proof assets โ saved as local markdown you control.
skill-evaluator
Evaluate AI skills across model tiers with blind testing and refinement recommendations.
agent-evolutions
Genetic exploration of solution spaces for AI coding agents โ gather a verifiable objective, evolve variants, apply the winner.
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.