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/sonofmagic/weapp-tailwindcss/claude-mdgit clone --depth 1 https://github.com/sonofmagic/weapp-tailwindcssWhat 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 | $0.01259 | $0.01259 |
| Opus 5 | $0.00629 | $0.00629 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
weapp-tailwindcss 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 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 — 131 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
weapp-tailwindcss is a Turbo-based monorepo that brings TailwindCSS atomic styling to mini-program (小程序) developers. It provides comprehensive TailwindCSS support for WeChat Mini Programs, Taro, uni-app, remax, mpx, and other mini-program frameworks across webpack, vite, rspack, rollup, rolldown, and gulp build tools.
Monorepo Structure
-
packages/ - Core packages including:
weapp-tailwindcss- Main package with CLI (weapp-tailwindcssorweapp-tw)@weapp-tailwindcss/shared- Shared utilities@weapp-tailwindcss/postcss- PostCSS plugin@weapp-tailwindcss/babel- Babel transformations@weapp-tailwindcss/logger- Logging utilitiestailwindcss-injector,tailwindcss-core-plugins-extractor,tailwindcss-config- Build tool integrations
-
packages-runtime/ - Runtime-specific implementations (vite, webpack integrations)
-
apps/ - Reserved workspace; mini-program demo projects have moved to
demo/ -
demo/ - Framework-specific demo projects for the retained Tailwind CSS v3/v4 matrix (gulp, mpx, Taro webpack/vite, uni-app vite, weapp-vite)
-
templates/ - Project templates for different frameworks
-
website/ - Documentation website
-
benchmark/ - Performance benchmarking tools
-
e2e/ - End-to-end tests with CSS snapshot testing
Common Development Commands
Build
pnpm build # Build all packages (uses turbo cache)
pnpm build:nocache # Build without cache (TURBO_FORCE=1)
pnpm build:apps # Build apps only
pnpm build:pkgs # Build packages only
pnpm build:docs # Build documentation website
pnpm build:demo # Build demo apps
Test
pnpm test # Run all tests (vitest)
pnpm test:dev # Run tests in watch mode
pnpm test:core # Run main package tests
pnpm test:plugins # Run plugin package tests
pnpm test:typography # Run typography tests
pnpm test:ui # Run tests with UI
pnpm e2e # Run end-to-end tests
pnpm e2e:u # Update e2e snapshots
pnpm bench # Run benchmarks
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 · 131 lines · 1,259 tokens per session scan A aad442796252
weapp-tailwindcss CLAUDE.md is an instructions file published in the GitHub repository sonofmagic/weapp-tailwindcss (1,855 stars, last pushed today), licensed MIT. It adds 1,259 tokens to every session, about $0.0063 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
weapp-vite CLAUDE.md
Instructions for weapp-vite/weapp-vite, covering claude.md, project overview, vue support, common commands and development.
weapp-vite AGENTS.md
Instructions for weapp-vite/weapp-vite, covering agents guidelines (global baseline), 1. monorepo routing, 2. fast-path commands (prefer smallest verification first), 2.1 dist sync guard (prevent stale cli/runtime) and 3. coding rules.
vital AGENTS.md
Instructions for jvidalv/vital, covering ai agent development guide, quick reference, component creation workflow, step 1: determine component level and step 2: create component files.
vital CLAUDE.md
Instructions for jvidalv/vital, covering claude ai assistant guide, project overview, tech stack, core framework and styling.
magicui AGENTS.md
Instructions for magicuidesign/magicui, covering project context, key principles, before writing code, rules and accessibility (a11y).
supermemory CLAUDE.md
Claude Code instructions for supermemoryai/supermemory, covering claude.md, repository structure, applications (apps/), development commands and root level (monorepo).