PM-driven development workflow with 6 specialized agents (explorer, planner, coder, tester, reviewer, documenter). Supports TypeScript/Python/Go/Rust.
Create design document with planner agent
PM-driven development workflow: discover → explore → design → implement → test → review → docs
Generate documentation with documenter agent
Analyze codebase with explorer agents
Search and browse past development session history
Code implementation, parallelizable across independent modules
Documentation generation and maintenance (README, API specs, architecture)
Deeply analyzes existing codebase by tracing execution paths, mapping architecture layers, understanding patterns, and documenting dependencies to inform design and implementation
Design documents and impact analysis for project requirements
Code review for quality and security after implementation
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.
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
Agents, unchained.
Just say what you want to build. 6 specialized agents handle the full cycle — exploration, design, implementation, testing, review, and documentation — automatically.
You: /devflow:dev "Add a chat feature using Gemini API"
DevFlow: Web UI or CLI? Save history?
You: Web UI. Session-only.
DevFlow: Which architecture?
[Option 1: Minimal] [Option 2: Clean] [Option 3: Balanced]
You: (clicks Option 2)
→ explore → design → code → test → review → docs → done
/plugin marketplace add shumatsumonobu/dotagents
/plugin install devflow@dotagents
| Scope | Usage |
|---|---|
| user (default) | Available across all projects |
| project | Shared with team via Git |
| local | Personal use, Git excluded |
Restart Claude Code, then /agents to verify.
MIT
shumatsumonobu (@shumatsumonobu)
npx claudepluginhub shumatsumonobu/dotagents --plugin devflowUnified toolkit for Context-Driven Development with spec-first planning, TDD workflow, and Beads integration
Universal Claude Code workflow with specialized agents, skills, hooks, and output styles for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
11 agents, 35 skills, 18 commands, 9 hooks — spec-driven multi-agent orchestration for Claude Code, with optional cross-device semantic memory.
HarnessFlow — From idea to shipped product: high-quality engineering workflows for AI agents. Spec-anchored SDD, gated TDD, evidence-based routing, independent reviews, and formal closeout.
Multi-agent /workflow development pipeline (planner → plan-review → coder → code-review) with typed handoff contracts, lifecycle hooks, and MCP servers.
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows