By Bayonle
Autonomous multi-agent SDLC workflow system with fresh context architecture. PM writes PRDs, Architect designs solutions, Engineer implements code, QA tests features, DevOps deploys to production. Each agent runs in isolated background context for scalability. Includes automatic git commits, documentation search via qmd, and complete task management.
Technical architect agent. Use proactively when a task needs system design, API contracts, or implementation planning. Spawns in fresh context.
DevOps deployment agent. Use proactively when a task needs deployment to production. Spawns in fresh context. Final agent in workflow.
Software engineer agent. Use proactively when a task needs code implementation, tests, or PR creation. Spawns in fresh context.
Domain expert PM agent. Use proactively when a task needs business requirements, user research, or PRD creation. Spawns in fresh context.
QA testing agent. Use proactively when a task needs testing, verification, or test reports. Spawns in fresh context.
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.
Autonomous multi-agent workflow system for Claude Code
PM writes PRDs → Architect designs → Engineer implements → QA tests → DevOps deploys
Full software development lifecycle automation with git commits, documentation search, and complete task management.
Fresh Context Design (v1.2.0): Each agent runs in isolated background context for scalability and accuracy.
/work orchestrator
↓
Spawns PM (Task tool, fresh context) → PRD → Exit
↓ (monitors completion)
Spawns Architect (fresh context) → Plan → Exit
↓
Spawns Engineer (fresh context) → Code → Exit
↓
Spawns QA (fresh context) → Tests → Exit
↓
Spawns DevOps (fresh context) → Deploy → Exit
↓
Complete!
Why Fresh Context?
✅ 5 Autonomous Agents - PM, Architect, Engineer, QA, DevOps ✅ Fresh Context Architecture - Each agent in isolated background context ✅ Resume Capability - Pick up from any phase ✅ Git Commits - Each phase commits work automatically ✅ Documentation Search - Integrated qmd CLI for research ✅ Task Management - File-based task tracking ✅ Zero Setup - Auto-initializes workspace on first use ✅ Works Anywhere - No per-project configuration needed
# Add the marketplace
/plugin marketplace add Bayonle/agentic-engineering
# Install the plugin
/plugin install agentic-workflow@agentic-engineering
Alternative - Local installation:
# Clone and install locally
git clone https://github.com/Bayonle/agentic-engineering.git
cd agentic-engineering
claude plugin install .
# Check plugin is installed
claude plugin list
# Test in any directory
cd ~/my-project
/pm --help
cd ~/my-project
# First use will auto-create workspace/
echo "Add user authentication" > workspace/tasks/inbox/task-001.md
/work task-001
That's it! The orchestrator will:
/work task-001 → spawns Architect → designs solution (you approve)/work task-001 → spawns Engineer → implements code/work task-001 → spawns QA → tests feature (you approve deployment)/work task-001 → spawns DevOps → deploys to productionEach agent runs in fresh context for accuracy and scalability!
/pm task-001 # PM only
/architect task-001 # Architect only
/engineer task-001 # Engineer only
/qa task-001 # QA only
/deploy task-001 # Deploy only
| Command | Agent | Purpose |
|---|---|---|
/work task-id | All | Full workflow PM→Architect→Engineer→QA→DevOps |
/task "title" [agent] [status] | - | Quick task creation and assignment |
/pm task-id | PM | Research requirements, write PRD |
/architect task-id | Architect | Design solution, create technical plan |
/engineer task-id | Engineer | Implement code, create PR |
/qa task-id | QA | Test feature, verify quality |
/deploy task-id | DevOps | Deploy to production |
# Create task in inbox
/task "Implement Swagger docs"
# Create and assign to engineer (skips PM/Architect)
/task "Add user auth" engineer
# Create with specific status
/task "Fix bug" engineer in-progress
npx claudepluginhub bayonle/agentic-engineering --plugin agentic-workflowClaude Code integration for MCP Task Orchestrator — schema-aware context, note-driven workflow
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
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
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.