By nWave-ai
Execute end-to-end feature development via phased AI waves—DISCOVER products with JTBD interviews, DISCUSS requirements and UX journeys, DESIGN architectures with C4 diagrams, DEVOPS infrastructure with Terraform/K8s, DISTILL BDD tests, DELIVER TDD code—enforced by 23 agents, automated reviews, and quality gates for production-ready outputs.
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD
Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.
Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.
Designs system architecture with C4 diagrams and technology selection. Use when defining component boundaries, choosing tech stacks, or creating architecture documents.
Designs CI/CD pipelines, infrastructure, observability, and deployment strategy. Use when preparing platform readiness for a feature.
Use for review and critique tasks - Acceptance criteria and BDD review specialist. Runs on Haiku for cost efficiency.
Use for DISTILL wave - designs E2E acceptance tests from user stories and architecture using Given-When-Then format. Creates executable specifications that drive Outside-In TDD development.
Use for review and critique tasks - Agent design and quality review specialist. Runs on Haiku for cost efficiency.
Use when creating new AI agents, validating agent specifications, optimizing command definitions, or ensuring compliance with Claude Code best practices. Creates focused, research-validated agents (200-400 lines) with Skills for domain knowledge. Also optimizes bloated command files into lean declarative definitions.
Use for review and critique tasks - Data architecture and pipeline review specialist. Runs on Haiku for cost efficiency.
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation
Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof
Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement
5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
No model invocation
Executes directly as bash, bypassing the AI model
AI agents that guide you from idea to working code — with you in control at every step.
nWave runs inside Claude Code. You describe what to build. Specialized agents handle requirements, architecture, test design, and implementation. You review and approve at each stage.
Starting with v2.8.0, all slash commands use hyphen format instead of colons.
| Before (v2.7.x) | After (v2.8.0+) |
|---|---|
/nw:deliver | /nw-deliver |
/nw:design | /nw-design |
/nw:discuss | /nw-discuss |
/nw:distill | /nw-distill |
/nw:discover | /nw-discover |
| All other commands | /nw-{command} |
Why? Commands migrated from Claude Code's dynamic commands/ directory to the stable skills/ system to prevent commands from disappearing during long sessions.
To upgrade: Run pipx upgrade nwave-ai && nwave-ai install (CLI) or /plugin marketplace update nwave-marketplace (plugin). Old /nw: commands are automatically removed.
match/case statements and X | Y union type syntax introduced in Python 3.10. Verify with python3 --version.From Claude Code, run:
/plugin marketplace add nwave-ai/nwave
/plugin install nw@nwave-marketplace
Restart Claude Code and type /nw- to see all available commands.
Install from PyPI — useful for contributing or environments without plugin support:
pipx install nwave-ai
nwave-ai install
Agents and commands go to ~/.claude/.
Don't have pipx? Install with:
pip install pipx && pipx ensurepath, then restart your terminal. Windows users: Use WSL (Windows Subsystem for Linux). Install with:wsl --install
Full setup details: Installation Guide
nWave also works with OpenCode, an open-source IDE for AI pair programming. Installation requires a few extra steps to configure OpenCode's environment.
Install prerequisites:
npm install -g opencode-ai
pipx install nwave-ai
Configure OpenCode:
mkdir -p ~/.config/opencode
echo '{"model": "openai/gpt-4o-mini"}' > ~/.config/opencode/opencode.json
Set your OpenAI API key:
export OPENAI_API_KEY=your-key-here
Install nWave into OpenCode:
nwave-ai install
Compatibility notes:
tool.execute.before mechanism/nw-discuss, /nw-design, /nw-distill, /nw-deliver commands for best results| Scenario | Use | Why |
|---|---|---|
| First time | Plugin | Zero dependencies, instant setup |
| Team rollout | Either | Plugin for simplicity, CLI for automation |
| Contributing | CLI | Dev scripts, internals access |
| Already on CLI | Either | Both coexist safely |
/nw-discuss "user login with email and password" # Requirements
/nw-design --architecture=hexagonal # Architecture
/nw-distill "user-login" # Acceptance tests
/nw-deliver # TDD implementation
Four commands. Four human checkpoints. One working feature.
Full walkthrough: Your First Feature
nWave checks for new versions when you open Claude Code. When available, you'll see a note in Claude's context with version details and changes.
Plugin (self-hosted marketplace):
/plugin marketplace update nwave-marketplace
Updates are available immediately after each release — no review delay.
Plugin (official Anthropic directory):
The official directory pins plugins to reviewed versions. Updates go through Anthropic's review process before reaching users. If you installed from the official directory and want the latest version sooner, add the self-hosted marketplace:
/plugin marketplace add nwave-ai/nwave
/plugin install nw@nwave-marketplace
CLI method:
pipx upgrade nwave-ai
nwave-ai install
Control check frequency via update_check.frequency in ~/.nwave/des-config.json: daily, weekly, every_session, or never.
Plugin method:
/plugin uninstall nw
CLI method:
nwave-ai uninstall # Remove agents, commands, config, DES hooks
pipx uninstall nwave-ai # Remove the Python package
npx claudepluginhub nwave-ai/nwave --plugin nwPersona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Helder's personal SDLC toolbelt for AI coding agents — from PRD to ship. Bundles the tracer-bullet workflow alongside TDD, code review, audits, and shipping skills.
Requirements-driven development workflow with quality gates for practical feature implementation
A TDD-driven iterative feedback loop for software development with Claude Code. 16 cohesive skills + 2 custom subagents walk an idea from brainstorm → plan → execute → tdd → iterate, with checkpoints throughout. Vertical-slice TDD, parallel coder/overseer review, no auto-commits. Single entry point: 'let's evanflow this'.
Plugin de ingeniería de software completa: 10 agentes de núcleo y 9 opcionales con personalidad propia, memoria persistente por proyecto, quality gates y flujos automatizados desde la idea hasta producción.
Spec-Driven Development Workflow for Claude Code. A 6-step pipeline: Requirements → Code Analysis → Design → Implement → Verify → Self-Improve. Specifications are the source of truth, code is a verified artifact.