What is vibe-coding-tw CLAUDE.md?

A repository guide for the Vibe Coding CN project, a collection of prompts, agent skills, documents, and tools for AI-assisted programming. It lists the project's main folders and common maintenance commands.

Use it when modifying this repository so the agent follows its structure and documented commands, including `make lint` and the prompt-library workflow.

It gives coding agents project-specific context and tells them how to manage prompts, lint Markdown files, create backups, and work with the conversion tool.

How godmakereth/vibe-coding-tw configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to godmakereth/vibe-coding-tw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/godmakereth/vibe-coding-tw/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/godmakereth/vibe-coding-tw

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/godmakereth/vibe-coding-tw/claude-md/github.svg)](https://agentmods.dev/instructions/godmakereth/vibe-coding-tw/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/godmakereth/vibe-coding-tw/claude-md"><img src="https://agentmods.dev/badge/instructions/godmakereth/vibe-coding-tw/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/godmakereth/vibe-coding-tw/claude-md"><img src="https://agentmods.dev/badge/instructions/godmakereth/vibe-coding-tw/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 511 This file is loaded in full into every session.

When invoked 511 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00511	$0.00511
Opus 5.5	$0.00204	$0.00204
Sonnet 5.5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured 2mo ago against content hash 2174f3638fa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vibe-coding-tw 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 2mo 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.

CLAUDE.md · 53 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude series models when working with code in this repository.

Repository Overview

This is the Vibe Coding CN repository, a workflow, toolset, and knowledge base for advanced AI-assisted programming. The project's core assets are its extensive prompts and skills libraries.

Key Commands

Prompt Library Management

# Enter the library directory
cd libs/external/prompts-library

# Run the interactive conversion tool
python3 main.py

Development & Maintenance

# Lint all markdown files in the repository
make lint

# Create a full project backup (respects .gitignore)
bash backups/一鍵備份.sh

Architecture & Structure

Core Directories

prompts/: The core asset. A massive, well-organized library of prompts.
- coding_prompts/, system_prompts/, user_prompts/
skills/: A modular library of skills for the AI, providing domain-specific knowledge for various tools like ccxt, postgresql, telegram-dev, etc.
documents/: The project's knowledge base, containing methodology, principles, and guides.
libs/external/prompts-library/: A Python-based tool for converting prompts between Excel and Markdown formats.
backups/: Scripts for project backups.
libs/: Skeleton for shared Python library code.

Key Technical Details

Prompt Organization: Prompts use a (row,col)_ prefix for categorization.
Conversion Tool: The prompts-library uses Python with pandas and openpyxl.
Documentation Standard: User-facing documentation is in Chinese. Code, file names, and structure are in English.
Skills: The skills directory provides context and knowledge for specific tools and domains, each with its own SKILL.md.

Development Workflow

When modifying this repository:

Follow the existing prompt and skill categorization systems.
Use the prompts-library tool to maintain consistency when updating prompts.
Run make lint after changing any Markdown files.
Run a backup with bash backups/一鍵備份.sh before any major refactoring.

Changes

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.

2mo ago First seen · 53 lines · 511 tokens per session scan A 2174f3638fa8

Subscribe to this mod's changes

vibe-coding-tw CLAUDE.md is an instructions file published in the GitHub repository godmakereth/vibe-coding-tw (48 stars, last pushed 10mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0020 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 2026-08-30.

vibe-coding-tw CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
vibe-coding-tw CLAUDE.mdgodmakereth/vibe-coding-tw	Instructions file	48	10mo ago	MIT	A	511	Claude Code
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
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
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

vibe-coding-tw: Instructions file for Claude Code