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-site/claude-mdgit clone --depth 1 https://github.com/posit-dev/py-shiny-siteWrote 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-site/claude-md)<a href="https://agentmods.dev/instructions/posit-dev/py-shiny-site/claude-md"><img src="https://agentmods.dev/badge/instructions/posit-dev/py-shiny-site/claude-md.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 | $0.06135 | $0.06135 |
| Opus 5 | $0.03068 | $0.03068 |
| Sonnet 5 | $0.01227 | $0.01227 |
| Haiku 4.5 | $0.00613 | $0.00613 |
Grade A, and why
py-shiny-site CLAUDE.md 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.
- **Release-asset downloads must be cached + retried:** github.com returns HTTP 503s and drops connections for unauthenticated release-asset downloads when many jobs ask at once — and one push here starts 10 site shards How it starts
The opening of the file, as written. The whole thing — 411 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.
Project Overview
This is the Shiny for Python documentation website - the official documentation, API reference, component gallery, and template showcase for the Shiny for Python framework. Built with Quarto, it combines hand-written conceptual documentation with auto-generated API reference docs extracted from the main py-shiny repository.
Commits and Pull Requests
Use Conventional Commits for both commit messages and PR titles. Format: <type>: <description> (or <type>(<scope>): <description>).
Common types in this repo: feat, fix, docs, ci, test, refactor, chore, build. Examples:
docs: add Accordion layout component pageci: verify shinylive links are up to datefix: point install-quarto at renamed site.yml workflow
Development Commands
Initial Setup
# Clone and initialize submodules
git clone https://github.com/posit-dev/py-shiny-site.git
cd py-shiny-site
make submodules
# Full build (creates venv, installs deps, generates API docs, builds site)
make all
Or, for any fresh checkout or git worktree, one command does submodules + deps
- generated docs and seeds
_build//render caches from a sibling checkout:
make ai-setup
(Conductor workspaces run this automatically via .conductor/settings.toml.)
Common Development Workflow
# One-command init for a fresh checkout/worktree (submodules, deps, generated
# docs; seeds _build/ and render caches from a sibling checkout when possible)
make ai-setup
# Serve with live preview. Runs a parallel full build first ONLY if _build/ is
# missing or older than _quarto.yml; otherwise starts instantly and re-renders
# just the pages you edit.
make serve
# Serve with a full SERIAL initial render (~35 min). Use after changing
# _quarto.yml, the SCSS theme, includes, or extensions — `make serve` skips
# the up-front full render, so site-wide config changes won't propagate there.
make serve-serial
# Full site build using local parallel shards (~9 min on a multi-core machine)
make site-parallel
# Full serial site build (the fidelity reference; what CI shards run internally)
make site
# Rebuild API documentation from py-shiny submodule
# (skips itself when the submodule commit, _renderer.py, quartodoc configs,
# and requirements.txt are unchanged — stamp file: .quartodoc-stamp)
make quartodoc
# Rebuild component previews and Shinylive links
make docs
# Clean build artifacts (also purges .quarto/shinylive-cache)
make clean
# Pull latest changes including submodules
git pull
make submodules
make all
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 · 411 lines · 6,135 tokens per session scan A a1c2420835a0
py-shiny-site CLAUDE.md is an instructions file published in the GitHub repository posit-dev/py-shiny-site (22 stars, last pushed 22d ago), licensed MIT. It adds 6,135 tokens to every session, about $0.0307 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 instructions, from other repositories
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).
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.
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.
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.