enzed/vibe-coding

Vibe Coding is a methodology guide for building games and applications using AI coding assistants like Claude Opus or Codex.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 7 minutes ago
Type:Curated List / Learning ResourceCategory(s):AI Coding AgentsGame DevelopmentAI Agents & LLM Apps
Added to GitGenius on September 14th, 2026
Created on March 12th, 2025
Open Issues & Pull Requests: 0 (+0)
GitHub issues: Enabled
Number of forks: 420
Total Stargazers: 4,784 (+0)
Total Subscribers: 62 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 30.1 days
Mean response time: 41.0 days
90th percentile: 67.0 days
Tracked items: 4

Most active contributors

Sign in to see contributor activity.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 0
New in 7 days: 0
Closed in 7 days: 0
Avg open age: N/A days
Stale 30+ days: 0
Stale 90+ days: 0

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

Vibe Coding is a methodology guide for building games and applications using AI coding assistants like Claude Opus or Codex.

The guide addresses the challenge of maintaining code quality and project coherence when relying on AI for development. It works by establishing a structured workflow that begins with human-driven planning rather than autonomous AI planning. The approach emphasizes creating a Game Design Document or Product Requirements Document first, defining a tech stack, and then using an AGENTS.md file with carefully configured rules to guide the AI assistant's code generation. The core principle is that planning must remain under human control to prevent the codebase from becoming unmanageable.

Developers should adopt this approach if they are building games or applications with AI assistance and want to maintain architectural integrity throughout development. The methodology suits projects where the developer is willing to invest time in upfront planning and rule configuration. The guide specifically recommends Claude Opus 4.7 or Codex 5.5 as the primary tools, noting that while earlier versions supported other models, the current approach has settled on these two. For developers considering Cursor, an older version of the guide exists but is noted as less powerful than the current recommendations.

The project is a living document that has evolved through multiple iterations, having transitioned between different AI models and tools as the author refined the methodology. The guide emphasizes that rules should be reviewed and manually adjusted by the developer, with critical rules marked as "Always" to ensure consistent AI behavior. The author stresses that over-engineering initial planning should be avoided in favor of iterative refinement, and that modularity in code organization must be actively enforced through the configured rules rather than left to the AI's discretion.