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 instructions/posit-dev/py-shiny/claude-mdgit 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 | $0.01991 | $0.01991 |
| Opus 5 | $0.00996 | $0.00996 |
| Sonnet 5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
py-shiny CLAUDE.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 today.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) 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 pyright (requires typings)
# 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 pinned 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
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 .claude/references/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.
- today Changed · -4 tokens per session 1e63a72e4c6e
- 2d ago First seen · 194 lines · 1,995 tokens per session scan A ebb47c0d69fe
py-shiny CLAUDE.md is an instructions file published in the GitHub repository posit-dev/py-shiny (1,750 stars, last pushed today), licensed MIT. It adds 1,991 tokens to every session, about $0.0100 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.