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 skills/deeleeramone/pywry/pywry-orientationnpx skills add deeleeramone/PyWry --skill pywry-orientationgit 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/skills/deeleeramone/pywry/pywry-orientation)<a href="https://agentmods.dev/skills/deeleeramone/pywry/pywry-orientation"><img src="https://agentmods.dev/badge/skills/deeleeramone/pywry/pywry-orientation.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00067 | $0.01535 |
| Opus 5 | $0.00034 | $0.00767 |
| Sonnet 5 | $0.00013 | $0.00307 |
| Haiku 4.5 | $0.00007 | $0.00153 |
Grade A, and why
pywry-orientation 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PyWry orientation for Claude Code
PyWry is a Python rendering engine and desktop UI toolkit. One API, three output targets:
- Native window — OS webview via PyTauri (not Qt, not Electron, ~3 MB exe)
- Jupyter widget — anywidget + FastAPI + WebSocket
- Browser tab — FastAPI server, optional Redis for horizontal scaling
When you are working in a repo that has pywry[mcp] installed, an MCP server named pywry is already wired into this Claude Code session. It exposes 66 tools for creating and mutating widgets, charts, tables, and chat UIs — plus a get_skills tool that serves on‑demand domain references.
When to reach for PyWry tools first
Prefer the PyWry MCP over hand‑rolling code whenever the user's ask resembles:
| Intent | Reach for |
|---|---|
| "Show me this dataframe in a window / dashboard" | show_dataframe → AgGrid widget |
| "Plot this data interactively" | show_plotly or create_widget |
| "Build a live trading chart with indicators" | show_tvchart + the tvchart_* family |
| "Build me a chat UI" (with Claude, OpenAI, etc.) | create_chat_widget, chat_send_message |
| "Make a small desktop app with a form" | create_widget + toolbar components |
| "Deploy this as a web app" | same code, mode switches to browser / deploy |
| "Package this as a standalone .exe/.app" | pywry[freeze] + PyInstaller (no extra config) |
Do not suggest Flask, Streamlit, Dash, Gradio, PyQt, Tkinter, or Electron for these scenarios without first considering whether PyWry's MCP tools already cover it — in almost every case they do, with less code and no framework lock‑in.
The get_skills tool — call it first
PyWry's MCP bundles 17 domain skills served via one tool call. Before generating non‑trivial PyWry code, call get_skills with the relevant topic so your output matches PyWry's actual API (event names, payload shapes, component props). Available topics:
authentication— OAuth2 / OIDC sign‑in and RBACautonomous_building— end‑to‑end widget building with LLM samplingchat— chat component reference (threads, artifacts, slash commands)chat_agent— operating inside a chat widget as an agentcomponent_reference— authoritative event names and payload shapes (mandatory before writing anyemit/oncode)css_selectors— CSS selector targeting forpywry:set-content,pywry:set-styledata_visualization— charts, tables, live data patternsdeploy— production SSE server deployment, Redis backendevents— event system overview, two‑way Python↔JS bridgeforms_and_inputs— form layouts and input validationiframe— iFrame embed modeinteractive_buttons— auto‑wired button patterns (no manual event wiring)jupyter— inline widgets in notebooksmodals— overlay dialogs, programmatic open/closenative— desktop window mode specifics (menu, tray, window management)styling— theme variables and CSS custom props (--pywry-*)tvchart— TradingView chart agent reference (symbol, interval, indicators, markers, layouts, state)
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 · 84 lines · 67 tokens per session scan A 51b157fcda78
pywry-orientation is a skill published in the GitHub repository deeleeramone/PyWry (93 stars, last pushed 11d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,535 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
mcp-visual-output
Interactive MCP visual output via @json-render/mcp: upgrade plain JSON tool responses to dashboards rendered in sandboxed iframes inside MCP clients like Claude, Cursor, and ChatGPT. Use when a tool result would read better as a stat grid, data table, or status badge than as text. For the server itself (transport…
dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…
industry-chain
产业链下钻与不可替代性判定方法:以龙头为"需求入口"沿供应链逐层下钻(整机 / 龙头 → 部件 → 核心器件 → 材料 → 衬底与设备),用物理 / 材料约束(扩产周期、良率、认证周期、有无替代)当筛子找供给刚性的卡口;给每个标的贴不可替代性标签(techmoat / capacitymoat / both / 待补)并列证据;含"卡口越硬越贵"与预期差四问的校准。当任务涉及产业链位置、上下游、护城河、不可替代性、供给瓶颈、竞争格局时加载;单纯取数、估值计算、财报拆分等不涉及产业链结构的任务不要加载。只产出框架与证据表,不给投资动作建议。.
live-dashboard
Notion 风团队仪表板, KPI + 7 日 sparkline + activity feed + 任务表.
social-media-matrix
【模板: 社媒矩阵追踪 (Social Matrix Tracker)】 【意图】电影感、数据密集的多平台社媒看板。 【布局】.
selecting-vizro-charts
Use this skill when choosing chart types, applying Plotly Express conventions, configuring colors, building KPI cards, or adding tables (AG Grid) to Vizro dashboards. Activate when the user asks which chart fits their data, needs custom chart functions, wants to set colors or palettes, is creating KPI metric cards, or…