Planning-first, design-driven development workflow with A/B design variants, architecture robustness checks, trunk-based development enforcement, predefined agent team swarms, compound knowledge accumulation, browser automation testing, feature video walkthroughs, git worktree management, lightweight fast-lane workflows, code simplification, parallel batch operations, and skill eval framework. Stack-agnostic with auto-detection.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Remove losing A/B variant, promote winner, clean up feature flags and tracking code
Analyze A/B test results, determine statistical significance, recommend winner, produce cleanup plan
Check status of all active A/B tests — shows test names, variants, duration, and flag status
Architecture robustness check with parallel security, performance, and data integrity reviews. Produces ADR.
Parallel codebase-wide changes using worktrees — wraps built-in /batch with project conventions, stack profile, and batch manifests
Sets up feature flags, analytics tracking, and the A/B test infrastructure for design variants. Auto-detects flag provider from stack profile.
Designs core architecture and authors Architecture Decision Records (ADRs) in MADR format. Evaluates trade-offs, proposes patterns, and documents rationale.
Classifies solved problems with validated YAML frontmatter — category, severity, module, tags — for searchability and pattern detection.
Compares stack profile against existing CLAUDE.md and suggests targeted additions. Never auto-writes — stages suggestions for user review.
Reviews code for style consistency, clean code principles, design patterns, and project convention adherence. Stack-adaptive — adjusts standards based on detected framework.
Production A/B testing lifecycle for design variants. Covers hypothesis formation, feature flags, variant comparison, analytics tracking, statistical significance analysis, experiment setup, and cleanup.
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
Multi-agent architecture review combining core architecture design with parallel security, performance, and data integrity assessments. Produces ADRs in MADR format. Covers ADR, architecture decision, system design, scalability assessment. Not for code review or implementation — for architectural decisions only.
Reference for how the built-in /batch command integrates with blueprint-dev workflows — parallel codebase-wide changes using worktrees with project context.
Analyzes detected stack profiles and suggests targeted CLAUDE.md improvements. Covers CLAUDE.md improvement, project configuration, AI instructions. Never auto-writes to CLAUDE.md — stages suggestions for user review.
Uses power tools
Uses Bash, Write, or Edit tools
A collection of Claude Code plugins by d.labs.
| Plugin | Description | Version |
|---|---|---|
| blueprint-dev | Planning-first, design-driven development workflow with A/B design variants, architecture robustness checks, trunk-based development enforcement, agent team swarms, compound knowledge accumulation, browser testing, git worktree management, lightweight fast-lane workflows, code simplification, parallel batch operations, and skill eval framework. | 2.0.0 |
| design-studio | Code-first design exploration workflow. Product planning, section screen design, brand discovery, variant generation, iterative refinement, token extraction, and production Next.js components using your project's component libraries (shadcn/ui, Radix UI). | 0.5.0 |
| scenario-testing | Probabilistic scenario validation for agentic software. LLM-judged user-story scenarios, satisfaction scoring across observed trajectories, and a Digital Twin Universe for behavioral clones of third-party services. | 0.1.0 |
Step 1: Add the marketplace:
claude plugin marketplace add https://github.com/dlabs/claude-marketplace
Step 2: Install a plugin:
claude plugin install blueprint-dev
claude plugin install design-studio
claude plugin install scenario-testing
This installs with user scope by default (available across all projects). To install for a single project only:
claude plugin install blueprint-dev --scope project
Step 3: Restart Claude Code for the plugin to take effect.
Planning-first, design-driven development workflow for Claude Code.
/discover to /compound, plus lightweight fast-lane, batch operations, browser testing, and video walkthroughs/blueprint-dev:bp:discover # Detect your stack
/blueprint-dev:bp:plan "feature" # Plan a feature
/blueprint-dev:bp:lfg "feature" # Full pipeline
/blueprint-dev:bp:go "small task" # Fast lane for small work
/blueprint-dev:bp:batch "change" # Parallel codebase-wide changes
/blueprint-dev:bp:test-browser # Browser tests on affected pages
See the full Blueprint-Dev Guide for detailed usage.
Code-first design exploration — from product definition to production components.
/design-studio:product # Define your product
/design-studio:design-brand # Build a Minimum Viable Brand
/design-studio:design "description" # Generate HTML design variants
/design-studio:design-pick # Pick a variant and extract tokens
/design-studio:design-ship # Convert to Next.js components
Probabilistic validation for agentic software — where traditional tests fall short.
/scenario-testing:author "user story" # Write a scenario from a user story
/scenario-testing:run # Execute scenarios against your system
/scenario-testing:score # Score satisfaction across trajectories
/scenario-testing:twin "service" # Create a behavioral clone of a service
MIT
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 claimnpx claudepluginhub dlabs/claude-marketplace --plugin blueprint-devProbabilistic scenario validation for agentic software. Replaces rigid tests with LLM-judged user-story scenarios, satisfaction scoring across observed trajectories, and a Digital Twin Universe for behavioral clones of third-party services. Designed for codebases where agents and LLMs are first-class design primitives.
dlabsCode-first design exploration workflow. Product planning → section screen design → brand discovery → variant generation → iterative refinement → token extraction → production components. Generate standalone HTML variants, design app screens scoped to sections, refine picked designs with feedback, extract design tokens, and ship as Next.js components using your project's component libraries (shadcn/ui, Radix UI).
dlabsFocused agentic engineering workflow: design-doc, spec, plan, implement, tdd, refactor, review, address-pr-feedback, browser-verify, explain-visually, compress, branch, and commit.
owainlewisStructured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.
alexiolanProduction-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
xiaobei930Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams
RatlerAgents for UI/UX design, accessibility, and user experience optimization
davepoonBlueprint Development methodology - structured feature development with PRD/PRP workflow, three-layer architecture (plugin/generated/custom), and documentation-first development
laurigates