Shiny for Python is a Python framework for building interactive web applications and data visualizations with reactive behavior. Data scientists and Python developers use it for prototypes as well as larger applications. Its bundled agent skills provide coding agents with Shiny documentation so they can create better Shiny applications.
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/py-shiny-releasenpx skills add posit-dev/py-shiny --skill py-shiny-releasegit clone --depth 1 https://github.com/posit-dev/py-shinyWrote 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/posit-dev/py-shiny/py-shiny-release)<a href="https://agentmods.dev/skills/posit-dev/py-shiny/py-shiny-release"><img src="https://agentmods.dev/badge/skills/posit-dev/py-shiny/py-shiny-release.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 | $0.00122 | $0.03638 |
| Opus 5 | $0.00061 | $0.01819 |
| Sonnet 5 | $0.00024 | $0.00728 |
| Haiku 4.5 | $0.00012 | $0.00364 |
Grade A, and why
py-shiny-release scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -m 3 -w "%{http_code}\n" http://localhost:3000/ || echo closed How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shiny for Python Release Train
Walk through releasing the full py-shiny ecosystem interactively. Each phase requires explicit user confirmation before proceeding to the next.
Interactive Protocol
- Present one phase at a time with its checklist
- After presenting a phase, stop and wait for the user to confirm completion or ask for help
- Use
ghCLI for GitHub operations (PRs, releases, tags) - Track progress with a TodoWrite checklist
- If the user says "skip", mark the phase done and move on
- If a phase fails, help debug before moving on
- Never proceed to the next phase until the current one is resolved or explicitly skipped
- Shut down every long-running process a phase started before marking it complete (see below)
Clean up background processes at the end of each phase
Several phases start servers or watchers that never exit on their own — most notably Phase 6's
make serve (a watch-mode dev server on port 3000). Left running, they hold ports, keep
rebuilding on file changes, and clutter the background task list for the rest of a release that
spans many hours.
When a phase is done, before marking it complete:
- Identify what the phase left behind, e.g.:
lsof -nP -iTCP:3000 -sTCP:LISTEN # Phase 6 `make serve` lsof -nP -iTCP:8100 -sTCP:LISTEN # Playwright's _shinylive webServer - Kill it and confirm the port actually closed, rather than assuming:
kill <pid> curl -s -o /dev/null -m 3 -w "%{http_code}\n" http://localhost:3000/ || echo closed - Say in the phase wrap-up which processes were shut down.
Only keep a server alive past its phase if a later step genuinely needs it, and say so
explicitly. Note that Playwright's own webServer (port 8100) stops itself when a run
finishes — it is make serve that lingers.
Watchers that poll CI or PyPI are fine to leave; they exit on their own. It is the servers that need killing.
Pre-release gate (REQUIRED before any release action)
What ships with it
2 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.
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 · 284 lines · 122 tokens per session scan A e7a3832cc888
py-shiny-release is a skill published in the GitHub repository posit-dev/py-shiny (1,750 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 3,638 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
publish-python-release
Build or publish nemo-switchyard Python distributions through the repository's GitHub Actions workflow. Use when asked to build a development wheel, cut a Python release, publish to PyPI, create a release tag, or debug .github/workflows/publish.yml.
python-packaging
Create distributable Python packages with proper project structure, setup.py/pyproject.toml, and publishing to PyPI. Use when packaging Python libraries, creating CLI tools, or distributing Python code.
pypi-release
This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPIAPITOKEN secret.
changelog-python-cliff-skill
Generate automated changelogs for Python projects using git-cliff with PEP 440 versioning support.
release
Releases Plain packages with intelligent version suggestions and parallel release notes generation. Use when releasing packages to PyPI.
plainx-release
Releases plainx packages with version suggestions, changelog generation, and git tagging. Use when releasing a package to PyPI.