vibecode-pro-max-kit
Plan-first AI coding workflow with gated phases and autopilot
Instructs the AI agent to act as an orchestrator that detects user intent, routes work to the right specialist sub-agent or skill, enforces the gated RIPER-5 workflow, and picks cost-efficient models and execution strategies for each phase.
All Skills in This Repository (33)
Pure Emerald Level Indicatorsvc-audit-context
Audit context routing and surface discoverability across Claude and Codex wiring.
vc-validate-findings
Generate Validate Contract with Net Gate status from Layer 1 and Layer 2 findings.
vc-generate-phase-program
Generate kickoff artifacts for multi-phase RIPER-5 programs with YAML frontmatter.
vc-debug
Trace root causes of bugs and failures through a four-phase investigation workflow.
vc-scenario
Decompose features across 12 dimensions to surface edge cases and testing targets.
vc-update
Automate vibecode harness updates with dry-run diff and backup.
vc-agent-browser
Automate long-running browser tasks via CLI with named sessions and ARIA snapshots.
vc-autoresearch
Coordinate gap-finding, fix, and verification loops until metrics improve.
vc-context-discovery
Index feature-group files and load domain-routed context for agent sessions.
vc-frontend-design
Convert design screenshots and videos into frontend code with accessibility and theming.
vc-plan-discovery
Discover related plan artifacts across feature folders and general-plans.
vc-audit-vc
Audit VC harness health across Claude/Codex parity and protocol wiring.
Frequently Asked Questions
FAQPage SchemaHow to install vibecode-pro-max-kit?βΌ
Run `npx skills add withkynam/vibecode-pro-max-kit --all -g -y` in your terminal to install the full kit globally. After installing, run the vc-setup skill inside your project to scaffold the workflow files.
What problem does vibecode-pro-max-kit solve?βΌ
It stops AI coding agents from rushing into code without a plan. A gated research-to-execution workflow, self-healing test loops, and on-disk progress notes keep long tasks on track even across sessions.
Which AI coding tools does it work with?βΌ
It works with Claude Code, Codex, Cursor, Windsurf, GitHub Copilot, and other agents that read standard SKILL.md and agent instruction files. It is stack-agnostic and fits any language or framework.
How does autopilot mode work?βΌ
You paste a single goal block and the agent runs phase after phase unattended, pausing only for irreversible or costly actions. Progress is written to disk so the run can resume in a fresh session.
Do I need coding experience to use this kit?βΌ
Basic familiarity helps, but the kit is designed for plain-English requests. The agent asks clarifying questions up front and handles planning, testing, and verification for you.
Related Repositories in Software Engineering
View All in Software Engineeringβopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core