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/deeleeramone/PyWryWrote 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/deeleeramone/pywry/pywry)<a href="https://agentmods.dev/plugins/deeleeramone/pywry/pywry"><img src="https://agentmods.dev/badge/plugins/deeleeramone/pywry/pywry/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 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/deeleeramone/pywry/pywry"><img src="https://agentmods.dev/badge/plugins/deeleeramone/pywry/pywry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
pywry 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 1mo 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
89% identical to pywry marketplace — 72 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": "pywry",
"version": "0.1.1",
"description": "Native Claude Code integration for PyWry — MCP tools for generating and rendering HTML components, chat artifacts, and building native, web, or Jupyter applications with live preview. Built-in support for AgGrid, Plotly, TradingView, and more.",
"author": {
"name": "PyWry",
"email": "[email protected]",
"url": "https://github.com/deeleeramone/PyWry"
},
"homepage": "https://github.com/deeleeramone/PyWry",
"repository": "https://github.com/deeleeramone/PyWry",
"license": "Apache-2.0",
"category": "data-visualization",
"keywords": [
"pywry",
"webview",
"tauri",
"plotly",
"tradingview",
"aggrid",
"dashboard",
"charting",
"visualization",
"data-science",
"finance",
"interactive",
"real-time",
"chat",
"llm",
"agent",
"artifact",
"jupyter",
"notebook",
"python",
"mcp"
]
}
What it installs
The manifest is a name and a version. 1 skill, 3 commands, 1 agent, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 215 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.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.
- 1mo ago First seen · 38 lines scan A b952d6324183
pywry is a plugin published in the GitHub repository deeleeramone/PyWry (98 stars, last pushed 4d 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. It is 89% identical to pywry marketplace, differing in 72 lines, and is treated as a copy.
Other plugins, from other repositories
surface
Surface — universal display for AI agents. Push HTML/CSS/JS to a PWA via the surface CLI; react to user clicks with surface wait. See SKILL.md.
ccc-dashboard
Skills for running a fleet of coding-agent sessions through Claude Command Center (CCC): spawn, message and check on sibling sessions, verify fixes, and hand off work. Needs CCC running locally.
powerbi-agent
Power BI dashboard building for AI agents: the powerbi-agent MCP server (list workspaces and items, model schema, read-only DAX, download/validate/deploy PBIR reports with guardrails, date-filter pins, page captures, refresh history) and three skills (build, review, verify). Needs Python 3.11+, pip install -r requirem.
claude-code-monitor
Local usage, cost and failure dashboard for Claude Code. Auto-starts on session start; open http://localhost:8787.
promptline
Local, read-only visual timeline of your Claude Code prompt history - dashboard, activity heatmap, and searchable per-project/session feed. Binds to 127.0.0.1 only, no outbound network calls, nothing written back to /.claude.
science-agent
Citation, prose, figure, and rigor auditing for AI-assisted research drafts.