Implementation session — execute milestones from a plan, write production code and tests, follow codebase patterns, surface deviations, maintain living docs. Launched via: claude --agent wf:builder
Maintenance session — continuous cleanup of LLM-generated technical debt in code and documentation. Keeps docs current, prunes stale plans, fixes drift. Launched via: claude --agent wf:gardener
Planning and design session — everything before code. Use when starting a feature, designing a system change, or breaking down complex work into an execution plan. Launched via: claude --agent wf:planner
Verification session — end-of-cycle quality review covering design, integrity, cleanliness, and production readiness. Delegates to specialized agents via Task tool. Launched via: claude --agent wf:verifier
Implementation practices — deviation protocol, progress tracking, code standards, codebase reflection
ALWAYS USE if you are the builder. Use after every implementation pass — update living docs, maintain diagrams (Mermaid for formal, ASCII for loose), reconcile plan with reality, update ARCHITECTURE.md when system shape changes. Documentation is a core output, not an afterthought.
The agent documentation system — doc types, folder structure, frontmatter conventions, agent roles, lifecycle
ALWAYS USE if you are the verifier or gardener. Use after any build cycle to audit documentation accuracy — check diagram drift, living doc freshness, ARCHITECTURE.md currency, cross-link integrity, and plan status. Gardener uses broadly across the full doc tree; verifier uses post-build to confirm the builder did its doc duty.
Testing philosophy — what good tests look like, anti-patterns, coverage priorities, naming
Executes bash commands
Hook triggers when Bash tool is used
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.
Stop vibe-coding. Ship with structure.
Plugins that make Claude Code follow a real development process.
No frameworks. No dependencies. No bloat. Just markdown files that work.
You: "Build me an auth system"
Claude: *writes 500 lines*
Claude: "Done! Here's your auth system."
You: *tests it*
You: "This doesn't actually validate tokens."
Claude: "Oh right, let me fix that..."
Claude: *writes 200 more lines that break something else*
LLMs skip steps. They write code that looks right but doesn't work. They forget what they were doing between sessions.
Every AI coding tool adds more features, more complexity, more noise. This goes the other way: simple markdown files that enforce discipline.
Most AI tools just generate. This one asks.
┌─────────────────────────────────────────────────────────────────────────┐
│ │
│ TYPICAL AI THIS WORKFLOW │
│ │
│ You: "Build auth" You: "Build auth" │
│ │ │ │
│ ▼ ▼ │
│ AI: *generates 500 lines* AI: "JWT or session-based? │
│ │ What's the token lifetime? │
│ ▼ Refresh token strategy?" │
│ You: "This is wrong" │ │
│ │ ▼ │
│ ▼ You: *answers* │
│ AI: *generates 300 more* │ │
│ │ ▼ │
│ ▼ AI: *builds exactly that* │
│ You: "Still wrong" │ │
│ │ ▼ │
│ ▼ AI: "I built X, Y, Z. │
│ *repeat until frustrated* Is that what you meant?" │
│ │ │
│ ▼ │
│ You: "Yes" or "No, actually..." │
│ │ │
│ ▼ │
│ *catches drift before it compounds*│
│ │
└─────────────────────────────────────────────────────────────────────────┘
Questions appear at every phase:
LLMs are confident. Confident and wrong. Questions force verification before the wrong code compounds into a mess.
┌────────────────────────────────────────────────────────────────────┐
│ │
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ │
│ │ PLAN │───▶│ BUILD │───▶│ VERIFY │───▶│ AUDIT │ │
│ └─────────┘ └─────────┘ └─────────┘ └─────────┘ │
│ │ │ │
│ │ ┌─────────┐ │ │
│ └─────────────▶│ FIX │◀───────────────────┘ │
│ └─────────┘ │
│ │
└────────────────────────────────────────────────────────────────────┘
Plan before you code. Track deviations. Audit for fake code. Fix systematically.
git clone https://github.com/jsai/claude-tooling.git
cd claude-tooling && ./install.sh
npx claudepluginhub jsai23/claude-tooling --plugin wfObsidian vault management: PARA filing, semantic search, backlinks, tags, inbox processing
Utility skills: documentation, context, handoffs
Agent loop management: launch, author session prompts, observe running loops
Auto-loop execution workflow with quality gates for Claude Code. Automatically decomposes tasks, implements code, runs tests, and iterates through quality gates until completion.
Core agents and commands required by all Developer Kit plugins
End-to-end development workflow: design → draft-plan → orchestrate → review → pr-create → pr-review → pr-merge
AI-powered development workflow automation - Phase-based planning, implementation orchestration, preflight code quality checks with security scanning, ship-it workflow, and development principles generator for CLAUDE.md
Production-ready Claude Code configuration with role-based workflows (PM→Lead→Designer→Dev→QA), safety hooks, 44 commands, 19 skills, 8 agents, 43 rules, 30 hook scripts across 19 events, auto-learning pipeline, hook profiles, and multi-language coding standards
Manifest-driven workflows for structured task execution with verification gates.