An example Claude Code project setup showing CLAUDE.md, hooks, skills, agents, slash commands, MCP servers and GitHub Actions workflows you can adapt.
OneRedOak/claude-code-workflows
A collection of Claude Code workflows, configs and guides for automating code review, security review and design review with AI agents.
- Stars
- 3,908
- Forks
- 560
- Open issues
- 9
- Last commit
- 13 days ago
What is it?
This repository collects workflows and configurations for Claude Code, Anthropic's coding agent, drawn from the author's experience building an AI-native startup. Each workflow is a self-contained folder with slash commands, agent definitions and, where applicable, GitHub Actions that run automatically on pull requests.
The three main workflows cover code review, which checks PRs for syntax, completeness, style guide adherence and bugs; security review, which flags vulnerabilities, exposed secrets and attack vectors with severity-classified findings based on OWASP Top 10; and design review, which uses Playwright MCP browser automation to check UI consistency, accessibility and visual issues in front-end changes.
The repository also hosts a downloadable companion guide, The Orchestration Layer Playbook, covering context, tools, workflows and verification around Claude Code and Codex, along with a 30-day rollout plan.
Key features
- 01Automated PR code review via slash commands and GitHub Actions
- 02Security review with severity-classified findings and remediation guidance
- 03Front-end design review using Playwright MCP browser automation
- 04Downloadable companion guide on orchestrating context, tools, workflows and verification
Use cases
- Adding an automated first-pass reviewer to a team's pull request process
- Scanning a codebase for exposed secrets and OWASP-style vulnerabilities
- Catching UI and accessibility regressions in front-end changes before release
Quick start
- 1
Browse the guide library and read the Orchestration Layer Playbook overview
- 2
Open the Code Review Workflow folder and follow its setup instructions
Things to know
- This is a collection of guides and configuration examples rather than a packaged tool, so setup is manual.
- The workflows are tied to Claude Code, and the design review workflow depends on Microsoft's Playwright MCP.
Topics
FAQ
- What is claude-code-workflows?
- A collection of Claude Code workflows, configs and guides for automating code review, security review and design review with AI agents. This repository collects workflows and configurations for Claude Code, Anthropic's coding agent, drawn from the author's experience building an AI-native startup. Each workflow is a self-contained folder with slash commands, agent definitions and, where applicable, GitHub Actions that run automatically on pull requests.
- Is claude-code-workflows free to use? What license does it have?
- claude-code-workflows is open source under the MIT license. Check the license terms before using it in commercial products.
- Is claude-code-workflows still maintained?
- Actively maintained. The last commit to claude-code-workflows was on Oct 9, 2026.
- What can I use claude-code-workflows for?
- Adding an automated first-pass reviewer to a team's pull request process Scanning a codebase for exposed secrets and OWASP-style vulnerabilities Catching UI and accessibility regressions in front-end changes before release
- How do I install claude-code-workflows?
- Browse the guide library and read the Orchestration Layer Playbook overview Open the Code Review Workflow folder and follow its setup instructions
- Where can I get claude-code-workflows?
- The source code and installation instructions are on GitHub: https://github.com/OneRedOak/claude-code-workflows
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A collection of Claude Code skills from HumanLayer for research, design, PR review visuals, and agentic coding workflows.
A GitHub Action that runs Claude Code on PRs and issues to answer questions, review changes, and implement code.
A GitHub Action that runs the Gemini CLI inside your repository to review pull requests, triage issues, and handle @gemini-cli requests.
A coding-agent skill that runs multi-phase security audits with isolated agents, independent verification, and machine-readable findings.
A Claude Code skill that turns a website URL into a 60 fps product launch video built from HTML, with music-synced sound effects and motion blur.