A systematic development workflow for producing high-quality, test-driven software. Integrates TDD, systematic debugging, verification gates, and agentic orchestration.
This folder contains **slash commands** - user-invoked prompts that execute specific workflows. Each `.md` file defines a command accessible via `/command-name` in Claude Code.
Quick test runner - run pytest and analyze results without permission prompts
Use for ALL technical failures. 4-phase root cause analysis before ANY fix attempts.
Architect mode - ULTRATHINK planning from GitHub Issue. Use for ALL new features and significant changes.
Use after completing a task to get code review before proceeding.
RAG-powered WebSocket protocol specialist for rugs.fun integration. Use PROACTIVELY when questions involve rugs.fun, REPLAYER, VECTRA-PLAYER, WebSocket events, gameStateUpdate, Socket.IO, or trading bot development. Provides authoritative answers about events, game mechanics, field definitions, and implementation patterns from indexed documentation.
QA Automation Engineer - writes tests only, pytest, TDD, test coverage
This folder contains **subagent definitions** - specialized AI assistants that Claude Code can delegate tasks to. Each agent has specific expertise and tool access.
Senior Python Developer - implements features to make tests pass, TDD workflow
Figma design specialist with full MCP integration and browser automation. Use when working with Figma designs, UI/UX implementation, design systems, component libraries, design-to-code workflows, or browser-based design validation. Can create, modify, and inspect Figma documents directly, and control browsers for visual testing.
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 systematic development workflow for producing high-quality, test-driven software with Claude Code.
Claude-Flow is a comprehensive development methodology that integrates:
| Principle | Command | Rule |
|---|---|---|
| TDD | /tdd | NO production code without failing test first |
| Verification | /verify | Evidence before claims, always |
| Debugging | /debug | NO fixes without root cause investigation |
| Planning | /plan | Plans must be executable with ZERO context |
| Isolation | /worktree | Isolated workspace for each feature |
cd ~/Desktop/claude-flow
./install.sh
# In Claude Code:
/plugin marketplace add ~/Desktop/claude-flow
/plugin install claude-flow@claude-flow-marketplace
claude-flow/
├── commands/ # Slash commands (/tdd, /debug, /verify, etc.)
├── agents/ # Specialized subagents (QA, Dev, GitHub, etc.)
├── skills/ # Agent skills (auto-invoked capabilities)
├── hooks/ # Workflow automation hooks
├── docs/ # Documentation
├── rag-pipeline/ # RAG knowledge system (future)
├── knowledge/ # Scraped documentation
└── integrations/ # External repos & tools
| Command | Description |
|---|---|
/tdd | Test-Driven Development workflow |
/debug | 4-phase systematic debugging |
/verify | Verification before completion |
/plan | ULTRATHINK planning from GitHub Issues |
/worktree | Git worktree for isolated development |
/review | Code review before proceeding |
/run-tests | Auto-detect and run test suite |
/scratchpad | Save/restore context |
/autotest | Quick test runner |
| Agent | Role |
|---|---|
@QA | Write tests, validate coverage |
@Dev | Implement features, write code |
@GitHub | PRs, issues, branches |
@ML-Engineer | ML/RL training, models |
@Sysadmin | System operations |
Control Claude's reasoning depth with keywords:
| Keyword | Tokens | Use For |
|---|---|---|
think | ~4k | Simple tasks |
think hard | ~10k | Debugging |
think harder | ~20k | Complex changes |
ultrathink | ~32k | Architecture |
Claude-Flow creates a closed-loop development system where the methodology enforces itself both locally (via Claude Code) and remotely (via GitHub Actions).
LOCAL (Claude Code) GITHUB (Actions)
───────────────────── ─────────────────
/tdd ◄───────────────────► Tests pass?
/verify ◄───────────────────► Validation checks
/review ◄───────────────────► Claude Code Action
| Workflow | Purpose |
|---|---|
validate.yml | Markdown lint, shell lint, plugin validation, self-dogfooding |
code-review.yml | Complexity analysis, security scanning, impact analysis |
claude.yml | AI-powered PR review using claude-flow methodology |
qodo-review.yml | Qodo AI-powered intelligent code analysis |
coverage.yml | Test coverage tracking with badges |
security.yml | CodeQL, Trivy, Bandit, dependency scanning |
pr-labeler.yml | Automatic PR labels based on changes |
release.yml | Tag-based releases with changelogs |
Mention @claude in any issue or PR comment to get AI-powered assistance. Add the claude-review label for automatic methodology review.
npx claudepluginhub joshuarweaver/cascade-ai-ml-agents-misc-2 --plugin dutchthenomad-claude-flowTest-driven development methodology with red-green-refactor cycles and code review
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'.
Unified toolkit for Context-Driven Development with spec-first planning, TDD workflow, and Beads integration
Test-driven development workflow for writing tests before implementation - red-green-refactor cycle with deterministic unit tests
Standalone tools: codebase audit, test audit, skill evaluation, and usage-window scheduling (queue / usage-guard)
Essential development commands for coding, debugging, testing, optimization, and documentation