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 brycewang-stanford/stata-codenpx agentmods add plugins/brycewang-stanford/stata-code/marketplacegit clone --depth 1 https://github.com/brycewang-stanford/stata-codeGrade A, and why
stata-code 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": "stata-code",
"owner": {
"name": "brycewang-stanford",
"url": "https://github.com/brycewang-stanford"
},
"metadata": {
"description": "Agent-native Stata bridge for empirical research — MCP server, Jupyter kernel, and VS Code extension sharing one token-economy v1.0 result schema, with one-call DiD/IV/RDD/table workflows and StatsPAI cross-validation.",
"version": "0.12.2"
},
"plugins": [
{
"name": "stata-code",
"source": ".",
"description": "Run Stata from Claude Code through the stata-code MCP server (21 tools, 14 workflow prompts, typed errors, token-economy logs/graphs, multi-session) and an agent skill that teaches Claude the result schema and modern DiD/IV/RDD/table workflows, including StatsPAI cross-validation.",
"version": "0.12.2",
"author": {
"name": "Bryce Wang",
"email": "[email protected]",
"url": "https://github.com/brycewang-stanford"
},
"homepage": "https://github.com/brycewang-stanford/stata-code",
"repository": "https://github.com/brycewang-stanford/stata-code",
"license": "MIT",
"category": "data-science",
"keywords": [
"stata",
"mcp",
"pystata",
"causal-inference",
"econometrics",
"jupyter"
]
}
]
}
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 · 37 lines scan A 2a2acf596ff7
stata-code is a plugin published in the GitHub repository brycewang-stanford/stata-code (41 stars, last pushed 21d 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
data2story-skill
Plugin marketplace listing 2 plugins: data2story, data2story-pro.
causal-powers
Causal Powers — a skills library for data analytics, causal inference, and reduced-form and structural econometrics.
data-scientist
快速数据分析：3 阶段流程（intake → execution → report），单 agent 完成，无多 agent 编排开销。.
agent-core
Skills for working with Fused as a Claude Code plugin: usage/guide skills for setting up Fused and building projects end-to-end (guide, setup, infra, cli, projects, execute, verify, storage, widgets, feedback). Load with claude --plugin-dir .
fused-marketplace
Fused plugins 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.