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.
Borrowing it
Nothing to install: this file belongs to posit-dev/py-shiny. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/posit-dev/py-shiny/main/AGENTS.mdgit 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/instructions/posit-dev/py-shiny/agents-md)<a href="https://agentmods.dev/instructions/posit-dev/py-shiny/agents-md"><img src="https://agentmods.dev/badge/instructions/posit-dev/py-shiny/agents-md/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/instructions/posit-dev/py-shiny/agents-md"><img src="https://agentmods.dev/badge/instructions/posit-dev/py-shiny/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02774 | $0.02774 |
| Opus 5.5 | $0.01110 | $0.01110 |
| Sonnet 5.5 | $0.00555 | $0.00555 |
| Haiku 4.5 | $0.00277 | $0.00277 |
Grade A, and why
py-shiny AGENTS.md 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 10d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents when working with code in this repository.
Overview
py-shiny is a Python web framework for building reactive web applications. It maintains feature parity with Shiny for R, often porting UI components from the R bslib package. The codebase consists of Python server-side code, TypeScript/JavaScript client-side code, and vendored assets from upstream packages.
Development Commands
Essential Commands
# Install dev dependencies (requires Python 3.10+)
pip install -e ".[dev,test,doc]"
pre-commit install # Optional: auto-format/lint on commit
# Format code (always run before committing)
make format # Auto-fix with black and isort
make check-format # Check only
make check-lint # Lint with flake8
# Type checking
make check-types # Run pyrefly (requires typings)
make check-pyright # Run pyright (separate CI job; run both before pushing)
# Run tests
make test # Unit tests only (pytest)
pytest tests/pytest/test_foo.py::test_name # Single unit test
make playwright # All end-to-end tests (slow)
make playwright-shiny SUB_FILE="inputs/test_foo.py" # Single test
# Comprehensive checks
make check # Format, lint, types, unit tests
make check-fix # Same but auto-fixes formatting
# Before opening a PR, run the checks through uv so the venv's toolchain is
# used (bare `make` may pick up a system black/isort/pyright with different
# versions and miss failures that CI catches, e.g. a py3.14 black target or a
# pyright error). This must pass:
uv run make format check-lint check-types check-pyright
Running Apps
shiny run app.py --reload --launch-browser # Dev server with auto-reload
SHINY_LOG_LEVEL=DEBUG shiny run app.py # Verbose logging
Asset Management
See memory-bank/assets.md for details.
# Vendor assets from upstream (bslib, shiny, sass, htmltools)
make upgrade-html-deps # Requires R installed
# Build JavaScript/TypeScript
make js-build # One-time build
make js-watch # Continuous rebuild
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.
- 10d ago Changed · +16 lines · +222 tokens per session c1f0f5f58817
- 22d ago Changed · +11 lines · +152 tokens per session f13386f0b9e6
- 23d ago First seen · 214 lines · 2,400 tokens per session scan A fe2099ec339b
py-shiny AGENTS.md is an instructions file published in the GitHub repository posit-dev/py-shiny (1,767 stars, last pushed yesterday), licensed MIT. It adds 2,774 tokens to every session, about $0.0111 per session on Opus 5.5. 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 2026-10-15.
py-shiny AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| py-shiny AGENTS.mdposit-dev/py-shiny | Instructions file | 1.8k | yesterday | MIT | A | 2,774 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |