Project architecture orchestrator with context-safe state management, Git-integrated checkpoints, and comprehensive blueprint generation. Features 6-phase workflow, research-backed recommendations, multi-agent coordination, validation system, and export capabilities.
Force a context refresh by re-reading all blueprint files and recent source changes. Use this when the conversation feels "drifted" or after a long chat session to re-seed Claude's context with accurate state.
Export blueprints to shareable formats like PDF, HTML, or Notion-compatible markdown.
Start the Framework Developer Orchestrator to plan and architect a new project through structured 6-phase discussion with blueprint generation
Quick 3-step planning for smaller projects. Skips the full 6-phase ceremony when you need a lightweight plan.
Rollback to a previous checkpoint state. Use when work needs to be reverted or to recover from errors.
Use when executing Phase 4 (Agent Assignment) of framework development - matching tasks to LLMs, estimating costs, and generating agent prompts. Skipped with --solo flag.
Use when executing Phase 1 (Discovery) of framework development - gathering project vision, creating outlines, making initial technology choices, and establishing verbal links.
Use when executing Phase 5 (Execution) of framework development - coordinating handoffs, tracking progress, enforcing quality gates, and managing checkpoints.
Use when a user wants to plan a new software project, architect a system, define module structure, coordinate multi-agent development, or resume a framework planning session.
Use when executing Phase 6 (Integration) of framework development - merging work, resolving conflicts, running integration tests, and generating the final report.
Use when defining API endpoints, designing request/response schemas, or establishing API contracts during framework planning.
Use when documenting architectural decisions, comparing technology options, or recording rationale for framework choices.
Use when selecting architecture patterns (MVC, hexagonal, clean, microservices) for a new project.
Use when creating or updating blueprint files in .framework-blueprints/ directory.
Use when designing CI/CD pipelines or creating GitHub Actions / GitLab CI configuration.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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 claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A curated collection of Claude Code plugins for development workflows - orchestration, code review, design, React development, and more.
| Plugin | Description | Category |
|---|---|---|
| orchestrate | Multi-agent parallel execution with file ownership | Development |
| brutal-review | Zero-tolerance multi-agent code review | Code Quality |
| design | Complete design thinking pipeline for UIs | Design |
| react-development | Comprehensive React with hooks and state management | Development |
| frontend-design | Production-grade frontend interfaces | Design |
| framework-dev | Project framework orchestrator (6-phase workflow) | Planning |
| ultraplan | Single-command planning: plain-English ideas → AI-executable plans | Planning |
Add to your ~/.claude/settings.json:
{
"extraKnownMarketplaces": {
"dev-workflow-skills": {
"source": {
"source": "github",
"repo": "Ankurjain1121/dev-workflow-skills"
}
}
},
"enabledPlugins": {
"dev-workflow-skills@orchestrate": true,
"dev-workflow-skills@brutal-review": true,
"dev-workflow-skills@design": true,
"dev-workflow-skills@react-development": true,
"dev-workflow-skills@frontend-design": true,
"dev-workflow-skills@framework-dev": true,
"dev-workflow-skills@ultraplan": true
}
}
Or install individual plugins by only enabling the ones you need.
Multi-agent parallel execution with file ownership
Fast parallel execution for large projects. One file = One owner. Supports multi-terminal mode with Claude/Gemini/Qwen.
/orchestrate add authentication with login, signup, and password reset
/orchestrate --multi # For 10+ files
Zero-tolerance multi-agent code review
5 specialized agents (Security, Architecture, Quality, Performance, Style) with weighted scoring. 95+ to pass.
/brutal-review src/
Complete design thinking pipeline for UIs
Transforms rough ideas into PRDs, runs 9-pass UX analysis, audits existing UIs, and iterates based on feedback.
/design "Create a dashboard for analytics"
Comprehensive React development
Hooks, components, state management, context, effects, and performance optimization based on official React documentation.
/react-development # Then ask React questions
Production-grade frontend interfaces
Create distinctive, polished code that avoids generic AI aesthetics. Anti-slop rules for high design quality.
/frontend-design "Build a landing page"
Project framework orchestrator
6-phase workflow from discovery to integration. Research-backed recommendations, multi-agent coordination, context hygiene.
/framework-dev "Help me plan my new SaaS project"
Single-command planning: plain-English ideas → AI-executable plans
6-phase pipeline: Understand (40-70 discovery questions) → Research (3 parallel agents) → Plan (PRD + technical plan with XML tasks) → Review (8-category checklist) → Validate (traceability matrix) → Output. Designed for no-coders.
/ultraplan "Build a task management app with team features"
/ultraplan update # Non-destructive update of affected sections
/ultraplan status # Show current progress
MIT License - see LICENSE file
Built by Ankur Jain with Claude Code
npx claudepluginhub ankurjain1121/dev-workflow-skills --plugin framework-devProject architecture orchestrator with premise challenge, 4 scope modes, implementation alternatives, dream state mapping, confidence-scored findings, outside voice review, autoplan auto-decisions, and context-safe blueprint generation.
Create distinctive, production-grade frontend interfaces with high design quality. Anti-slop rules for polished code.
Comprehensive React development with hooks, components, state management, context, effects, and performance optimization.
Complete design thinking pipeline for UIs. Transforms ideas into PRDs, runs 9-pass UX analysis, and iterates based on feedback.
Multi-agent parallel execution with file ownership. One file = One owner. Maximum speed.
Structured project planning and execution through brainstorm, spec, and build phases across three execution tiers: sequential, delegated sub-agents, and full agent teams
Structured development skills for any project. Provides brainstorming, planning, parallel agent development, browser testing, systematic debugging, and self-improvement workflows.
Flow framework - Ultra-lightweight installer. Run /flow-init to download all 29 commands + 8 skills + 1 Claude agent
11 agents, 35 skills, 18 commands, 9 hooks — spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows