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/posit-dev/py-shiny/shiny-for-pythonnpx skills add posit-dev/py-shiny --skill shiny-for-pythongit clone --depth 1 https://github.com/posit-dev/py-shinyWhat 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 | $0.00209 | $0.01436 |
| Opus 5 | $0.00105 | $0.00718 |
| Sonnet 5 | $0.00042 | $0.00287 |
| Haiku 4.5 | $0.00021 | $0.00144 |
Grade A, and why
shiny-for-python 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 2d 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.
Shiny for Python
Shiny for Python (py-shiny) builds reactive web apps in pure Python. Two modes:
Core (an explicit app_ui object plus a server(input, output, session)
function) and Express (top-level code in the app file is the UI, with
outputs defined inline). The reactive graph is the engine: reading a reactive
source (input.x(), a reactive.value, a @reactive.calc) inside a reactive
context registers a dependency, so changing that source re-runs everything that
read it — you never call outputs or schedule updates yourself.
This skill is an index. Find your task below and read the linked reference file before writing code for that area.
Foundations
| Topic | Use when | Reference |
|---|---|---|
| Reactivity | A value should recompute or an output update as inputs change; choosing between calc / effect / value; req, isolate, timers, polling |
references/reactivity.md |
| Express mode | Writing or converting an Express app (from shiny.express import ...); context-manager layout; page_opts, @expressify |
references/express.md |
| Modules (Core) | A reusable, repeatable UI+server component in a Core app; avoiding input/output id collisions across copies | references/modules-core.md |
| Modules (Express) | The same reusable-component need in an Express app, via the single @module decorator |
references/modules-express.md |
| Session lifecycle | Per-session cleanup (on_ended), reading request headers/cookies/URL, flush hooks, per-session routes |
references/session-lifecycle.md |
Dashboard building
| Topic | Use when | Reference |
|---|---|---|
| Dashboard design | Turning a dataset or brief into a polished analytical dashboard; planning information hierarchy, shared filters, responsive layout, empty states, and the final visual/functional quality pass | references/dashboard-design.md |
| Dashboard components | Composing cards, KPI value boxes, local card toolbars, accessible icons, tooltips, and popovers | references/dashboard-components.md |
| Interactive charts | Rendering Plotly charts with shinywidgets; choosing chart forms, applying a coherent visual system, formatting hover/data labels, and handling empty data | references/interactive-charts.md |
| Maps | Choosing and rendering a geographic widget; cleaning coordinates, avoiding overplotting, and selecting Plotly, ipyleaflet, or lonboard by interaction and scale | references/maps.md |
What ships with it
26 files beside SKILL.md 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.
- references/bookmarking.md 6.2 KB
- references/chat.md 5.6 KB
- references/custom-components.md 5.6 KB
- references/custom-renderers.md 5.7 KB
- references/dashboard-components.md 5.4 KB
- references/dashboard-design.md 6.0 KB
- references/data-frames.md 5.4 KB
- references/debugging.md 4.7 KB
- references/dynamic-ui.md 5.3 KB
- references/express.md 5.9 KB
- references/extended-tasks.md 4.8 KB
- references/feedback.md 5.6 KB
- references/files.md 5.3 KB
- references/interactive-charts.md 5.0 KB
- references/layouts.md 5.2 KB
- references/maps.md 6.2 KB
- references/markdown-streaming.md 4.6 KB
- references/modules-core.md 6.0 KB
- references/modules-express.md 3.3 KB
- references/navigation.md 5.7 KB
- references/otel.md 5.0 KB
- references/plots.md 5.4 KB
- references/reactivity.md 5.7 KB
- references/session-lifecycle.md 6.0 KB
- references/testing.md 6.1 KB
- references/theming.md 6.4 KB
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.
- 2d ago First seen · 84 lines · 209 tokens per session scan A 9299962ea6d1
shiny-for-python is a skill published in the GitHub repository posit-dev/py-shiny (1,750 stars, last pushed 3d ago), licensed MIT. It adds 209 tokens to every session and 1,436 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…