Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/swt-labs/vibe-better-with-claude-code-vbw/llms.txt

Use this file to discover all available pages before exploring further.

VBW (Vibe Better With Claude Code) is a Claude Code plugin, not a standalone tool. You install it with /plugin install inside Claude Code, and it gives you a complete development lifecycle: phased planning, parallel agent execution, continuous verification, and persistent state across sessions.
VBW requires Claude Code v1.0.33+ and Opus 4.6+. It runs on macOS and Linux only. If you’re on Windows, use Claude Code inside WSL.

The core workflow

Every VBW project follows the same loop. You only need to remember two commands.
/vbw:init
Run once per project. VBW scaffolds .vbw-planning/, configures Agent Teams, installs git hooks, and suggests relevant skills. For existing codebases, it auto-chains to /vbw:map first — running 4 Scout agents in parallel to analyze your code before planning begins.
/vbw:vibe
The one command. Run it repeatedly. VBW auto-detects where your project is and does the right thing at each stage: scope requirements, create a phased roadmap, plan the next phase, execute it with parallel Dev agents, run QA verification. State persists in .vbw-planning/ across sessions, so you can close your terminal and pick up exactly where you left off.
/vbw:vibe --archive
When all phases are complete, archive the work. VBW runs a completion audit, archives state to .vbw-planning/milestones/, and tags the git release. That’s the entire lifecycle: /vbw:init/vbw:vibe (repeat) → /vbw:vibe --archive.

Key capabilities

Agent teams

Seven specialized agents — Scout, Architect, Lead, Dev, QA, Debugger, and Docs — each with platform-enforced tool permissions that can’t be bypassed during compaction.

Native hooks

22 hooks across 11 event types run automatically for security filtering, commit validation, task gating, session lifecycle, and post-compaction verification.

Three-tier verification

Goal-backward QA runs after every phase. The file-guard.sh hook blocks writes to files outside a Dev agent’s declared ownership. Database safety intercepts 40+ destructive patterns before they reach the shell.

Real-time statusline

Five or six lines of situational awareness rendered after every response — phase progress, plan completion, effort profile, QA status, and agent health.

Session resumption

/vbw:resume reads ground truth directly from .vbw-planning/ files without requiring a prior /vbw:pause. It detects interrupted builds and tells you exactly what to do next.

Skills.sh integration

Auto-detects your tech stack during /vbw:init and recommends relevant skills from the open registry. Run /vbw:skills anytime to browse and install more.

Token efficiency

Every new VBW capability runs as a bash subprocess at zero model token cost. Here’s how VBW’s coordination overhead compares to running stock Opus 4.6 agent teams manually:
CategoryStock agent teamsVBWSaving
Base context overhead10,800 tokens1,500 tokens86%
State computation per command1,300 tokens200 tokens85%
Agent coordination (×4 agents)16,000 tokens1,200 tokens93%
Compaction recovery5,000 tokens700 tokens86%
Context duplication (shared files)16,500 tokens900 tokens95%
Total coordination overhead87,100 tokens12,100 tokens86%
For subscription users, the reduction translates to roughly 3× more phases per rate limit cycle — 200% more development capacity for the same price. For API users, per-phase cost drops from 2.78to2.78 to 1.40 on the Balanced profile.

Platform requirements

  • Operating system: macOS or Linux. Windows requires WSL.
  • Claude Code: v1.0.33 or later (recommended: v2.1.47+ for full feature compatibility).
  • Model: Opus 4.6 or later.
  • Shell: bash (all hooks and scripts run as bash subprocesses).
  • jq: the only external dependency — brew install jq (macOS) or apt install jq (Linux).

Next step

Install VBW

Two commands inside Claude Code. No manual setup required.

Build docs developers (and LLMs) love