Configure Maestro for mobile app testing
Configure Playwright for web app testing
Initialize Beads task tracking in this project
Configure Claude Code permissions for agents
Consolidate and optimize CLAUDE.md
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A guided AI pipeline that takes you from "I have an idea" to working software. Scaffold walks you through 29 structured prompts — run them in order, and Claude Code handles the research, planning, and implementation for you.
By the end, you'll have a fully planned, standards-documented, implementation-ready project with working code.
Scaffold is a pipeline of AI-powered prompts designed for Claude Code, Anthropic's command-line coding tool. If you have an idea for a software project but don't know where to start — or you want to make sure your project is set up with solid architecture, standards, and tests from day one — Scaffold guides you through every step.
Here's how it works: you install Scaffold, then run slash commands like /scaffold:create-prd in Claude Code. Each command is a carefully structured prompt that tells Claude exactly what to research, what decisions to make, and what files to create. You don't need to write the prompts yourself — just run the commands and answer Claude's questions along the way.
Each step in the pipeline produces a specific artifact — a planning document, a configuration file, a standards guide, or actual code — and then tells you exactly which command to run next. You follow the chain from defining your product all the way through to a working implementation.
Before using Scaffold, you'll need the following tools installed:
Node.js (v18 or later) Needed for Beads and most modern JavaScript/TypeScript projects.
brew install nodenode --versionGit Needed for version control and Beads task tracking.
brew install gitgit --versionClaude Code The AI coding assistant that runs the Scaffold prompts. Claude Code is a command-line tool from Anthropic — it's not the same as the Claude web chat.
npm install -g @anthropic-ai/claude-codeclaude --versionBeads
A git-backed task tracker designed for AI agents. Scaffold uses Beads (bd) to create and manage the task graph that drives implementation. Think of it as a to-do list that both you and Claude can read and update.
npm install -g @beads/bdbd --versionPlaywright MCP (web apps only) Lets Claude control a real browser for visual testing and screenshots. MCP (Model Context Protocol) is a way for Claude to use external tools — in this case, a headless browser.
claude mcp add playwright npx @playwright/mcp@latestChatGPT subscription (for multi-model review)
One optional step (multi-model-review) sets up automated code review using both Claude and OpenAI's Codex. This requires a ChatGPT subscription (Plus, Pro, or Team) — reviews use credits (~25 per review) with weekly limits that vary by plan. You can skip this step entirely if you don't have one.
Codex CLI and/or Gemini CLI (for user stories multi-model review)
One optional step (user-stories-multi-model-review) runs independent AI reviewers against your user stories to catch gaps a single model might miss. You need at least one of: Codex CLI (requires ChatGPT subscription) or Gemini CLI (free tier available). See Multi-Model Stories Review Setup for detailed instructions.
There are two ways to install Scaffold. Both give you the same commands — the only difference is the prefix you type.
Open Claude Code and run:
/plugin marketplace add zigrivers/scaffold
Then install the plugin:
/plugin install scaffold@zigrivers-scaffold
After installing, commands are available as /scaffold:command-name (for example, /scaffold:create-prd).
What's a plugin? Claude Code plugins are add-on command packages. When you install one, its commands become available as slash commands you can run in any Claude Code session. The plugin prefix (/scaffold:) keeps them organized and separate from other commands.
If you prefer a shorter prefix, clone the repo and run the install script:
git clone https://github.com/zigrivers/scaffold
cd scaffold && ./scripts/install.sh
Commands are available as /user:command-name (for example, /user:create-prd).
To uninstall later: ./scripts/uninstall.sh
After installing, open Claude Code and run:
/scaffold:prompt-pipeline
(or /user:prompt-pipeline if you used Option 2)
This prints the full pipeline reference. If you see a table of phases and commands, you're all set.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
npx claudepluginhub zigrivers/oc-scaffold --plugin scaffold11 agents, 35 skills, 18 commands, 9 hooks — spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
Automation bootstrap for Claude Code. Analyzes any project and generates a complete .claude/ structure with agents, pipelines, skills, memory, hooks, and settings.
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
Describe your goal, approve the spec, then step away — Claude and Codex loop together until it's right.