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.

vibe-coding-tw CLAUDE.md — Instructions file by godmakereth

Install

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.

agentmods

npx agentmods add instructions/godmakereth/vibe-coding-tw/claude-md

Clone the repo

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

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. Scan, not verified.

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	$0.00511	$0.00511
Opus 5	$0.00255	$0.00255
Sonnet 5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured 3d ago against content hash 2174f3638fa8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

3d 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 (47 stars, last pushed 8mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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.

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).

microsoft/vscode · 6,785 tokens

vibe-coding-tw CLAUDE.md