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 kennethkhoocy/applied-micro-skillsnpx agentmods add plugins/kennethkhoocy/applied-micro-skills/applied-microgit clone --depth 1 https://github.com/kennethkhoocy/applied-micro-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/kennethkhoocy/applied-micro-skills/applied-micro)<a href="https://agentmods.dev/plugins/kennethkhoocy/applied-micro-skills/applied-micro"><img src="https://agentmods.dev/badge/plugins/kennethkhoocy/applied-micro-skills/applied-micro.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
applied-micro 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 5d 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
86% identical to applied-micro-skills marketplace — 15 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": "applied-micro",
"version": "1.0.0",
"description": "Claude Code skills for empirical applied-micro research: reproducibility auditing, LLM-pipeline methods, event studies, WRDS, Stata, publication-grade tables",
"author": {
"name": "Kenneth Khoo",
"url": "https://github.com/kennethkhoocy"
}
}
What it installs
The manifest is a name and a version. 17 skills travel with it, and installing the plugin installs all of them — 2,984 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill latex-empirical-tables A 240 tokens
- Skill wrds A 107 tokens
- Skill cite-placement A 181 tokens
- Skill event-study-cars A 153 tokens
- Skill adversarial-empirical-review A 208 tokens
- Skill stata A 165 tokens
- Skill latex-to-word A 228 tokens
- Skill markdown-to-pdf A 188 tokens
- Skill asyncopenai-concurrency-httpx-pool A 161 tokens
- Skill download-gated-pdfs A 137 tokens
- Skill stata-style-figures A 130 tokens
- Skill annotator-input-parity-check A 207 tokens
- Skill llm-campaign-drift-gate A 179 tokens
- Skill adjudication-sheets A 142 tokens
- Skill llm-gold-bound-failure-check A 182 tokens
- Skill pyfixest-grid-sharding A 212 tokens
- Skill pyfixest-cupy64-absorbed-regressors A 164 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.
- 5d ago First seen · 10 lines scan A 82f091373236
applied-micro is a plugin published in the GitHub repository kennethkhoocy/applied-micro-skills (28 stars, last pushed today), 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 86% identical to applied-micro-skills marketplace, differing in 15 lines, and is treated as a copy.
Other plugins, from other repositories
ieee-skills
Bilingual skills for writing IEEE communications-journal papers (JSAC, TWC, TC/TCOM, WCL, CL): literature search with DOI/BibTeX verification, drafting with target-journal routing, learning-based and emerging-paradigm system models, reproducible methods, language polishing, IEEE citation/IEEEtran formatting…
codeweaver
skillrx
Security scanner for AI agent skills and plugins (Claude Code, Codex, Cursor, and 40+ more).
infras-kit
Infrastructure ticket-to-plan-to-implementation workflow and skill pack for Claude Code.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.