PDCA methodology + CTO-Led Agent Teams + AI coding assistant mastery for AI-native development
bkit is a Claude Code plugin that transforms how you build software with AI. It provides structured development workflows, automatic documentation, and intelligent code assistance through the PDCA (Plan-Do-Check-Act) methodology.
Context Engineering is the systematic curation of context tokens for optimal LLM inference—going beyond simple prompt crafting to build entire systems that consistently guide AI behavior.
Traditional Prompt Engineering:
"The art of writing good prompts"
Context Engineering:
"The art of designing systems that integrate prompts, tools, and state
to provide LLMs with optimal context for inference"
bkit is a practical implementation of Context Engineering, providing a systematic context management system for Claude Code.
bkit implements Context Engineering through three interconnected layers:
| Layer | Components | Purpose |
|---|---|---|
| Domain Knowledge | 27 Skills | Structured expert knowledge (phases, levels, specialized domains) |
| Behavioral Rules | 16 Agents | Role-based constraints with model selection (opus/sonnet/haiku) |
| State Management | 241 Functions | PDCA status, intent detection, ambiguity scoring, multi-feature context, team coordination |
Context injection occurs at five distinct layers:
Layer 1: hooks.json (Global) → SessionStart, UserPromptSubmit, PreCompact, PreToolUse, PostToolUse, Stop
Layer 2: Skill Frontmatter → Domain-specific hooks (deprecated in v1.4.4, use hooks.json)
Layer 3: Agent Frontmatter → Task-specific hooks with constraints
Layer 4: Description Triggers → Semantic matching in 8 languages
Layer 5: Scripts (45 modules) → Actual Node.js execution logic with unified handlers
Learn more: See Context Engineering Principles for detailed implementation.
- Plan Plus Skill (v1.5.5) - Brainstorming-enhanced PDCA planning with intent discovery, alternatives exploration, and YAGNI review
- bkend MCP Accuracy Fix (v1.5.4) - MCP tool coverage 19→28+, accurate tool names, dynamic Base URL, search_docs workflow
- Team Visibility & State Writer (v1.5.3) - Agent Teams state management with
.bkit/agent-state.jsonfor Studio IPC - SubagentStart/SubagentStop Hooks (v1.5.3) - 2 new hook events for agent lifecycle tracking (10 hook events total)
- Output Styles Auto-Discovery (v1.5.3) -
outputStylesin plugin.json + 4th stylebkit-pdca-enterprise - CTO-Led Agent Teams (v1.5.1) - CTO agent orchestrates parallel PDCA execution with multi-agent teams (Dynamic: 3, Enterprise: 5 teammates)
- Output Styles (v1.5.1) - Level-based response formatting (bkit-learning, bkit-pdca-guide, bkit-enterprise, bkit-pdca-enterprise)
- Agent Memory (v1.5.1) - Cross-session context persistence for all 16 agents (auto-active)
- Natural Feature Discovery (v1.5.1) - Auto-trigger integration aligned with "Automation First" philosophy
- Task Management + PDCA Integration (v1.4.7) - Task Chain Auto-Creation, Task ID Persistence, Check↔Act Iteration
- Core Modularization (v1.4.7) - lib/common.js split into 5 modules (lib/core/, lib/pdca/, lib/intent/, lib/task/, lib/team/)
- Context Engineering (v1.4.4) - Systematic context curation with 7 library modules and unified hook system
- PDCA Methodology - Structured development workflow with automatic documentation
- PDCA Skill Integration (v1.4.4) - Unified
/pdcaskill with 8 actions (plan, design, do, analyze, iterate, report, status, next) - Evaluator-Optimizer Pattern - Automatic iteration cycles from Anthropic's agent architecture
- 9-Stage Development Pipeline - From schema design to deployment
- 3 Project Levels - Starter (static), Dynamic (fullstack), Enterprise (microservices)
- Multilingual Support - 8 languages (EN, KO, JA, ZH, ES, FR, DE, IT)
- 27 Skills - Domain-specific knowledge for various development scenarios
- 16 Agents - Specialized AI assistants including CTO-Led Team agents
- 45 Scripts - Hook execution with unified handlers (hooks-json-integration)
- 241 Utility Functions - 5 modular libraries with state management, intent detection, task tracking, team coordination
- Check-Act Iteration Loop - Automatic gap analysis and fix cycles with max 5 iterations (90% threshold)
First time using Claude Code?
Start with bkit-starter!
- Beginner-friendly guide
- No programming experience required
- Build your first project hands-on
/plugin enable bkit-starterbkit is the advanced extension designed for users who have mastered bkit-starter.
| Requirement | Minimum Version | Notes |
|---|---|---|
| Claude Code | v2.1.33+ | Required. bkit uses hook events (TeammateIdle, TaskCompleted) introduced in v2.1.33. Older versions will fail to load hooks.json with a validation error. |
| Node.js | v18+ | For hook script execution |
| Agent Teams (optional) | Set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 |
Required only for CTO-Led Agent Teams feature |
Troubleshooting: If you see
"Failed to load hooks"error after installation, update Claude Code to the latest version:claude update
Note: bkit is designed for Claude Code. For Gemini CLI, see bkit-gemini.
The easiest way to install bkit is through the Claude Code marketplace.
# Step 1: Add bkit marketplace
/plugin marketplace add popup-studio-ai/bkit-claude-code
# Step 2: Install bkit plugin
/plugin install bkitUse /plugin command and navigate to Marketplaces tab to manage your plugin sources:
- bkit-marketplace: Contains bkit and bkit-starter plugins
- claude-plugins-official: Official Anthropic plugins
Navigate to Discover tab to browse and install available plugins:
| Plugin | Description | Best For |
|---|---|---|
| bkit | Full PDCA methodology + Claude Code mastery | Experienced developers |
| bkit-starter | Korean learning guide for beginners | First-time Claude Code users |
Keep your plugins up-to-date automatically by configuring auto-update in your settings:
// ~/.claude/settings.json
{
"plugins": {
"autoUpdate": true
}
}Update Commands:
- Press
uin the Marketplaces view to update all plugins - Press
rto remove a marketplace - Use
Spaceto toggle plugin selection in Discover view
bkit-claude-code/
├── .claude-plugin/
│ ├── plugin.json # Claude Code plugin manifest
│ └── marketplace.json # Marketplace registry
├── agents/ # Specialized AI agents
├── skills/ # Domain knowledge
├── hooks/ # Event hooks (hooks.json)
├── scripts/ # Hook execution scripts
├── lib/ # Shared utilities (5 modules)
├── output-styles/ # Level-based response formatting
├── templates/ # Document templates
└── bkit.config.json # Centralized configuration
After installing bkit via the marketplace, you can customize any component by copying it to your project's .claude/ folder.
Comprehensive Guide: See CUSTOMIZATION-GUIDE.md for detailed instructions on customizing bkit for your organization, including platform-specific paths, component examples, and license attribution requirements.
Claude Code searches for configuration files in this priority order:
- Project
.claude/(highest priority - your customizations) - User
~/.claude/ - Plugin installation (default)
# Step 1: Find the plugin installation location
ls ~/.claude/plugins/bkit/
# Step 2: Copy only the files you want to customize
mkdir -p .claude/skills/starter
cp ~/.claude/plugins/bkit/skills/starter/SKILL.md .claude/skills/starter/
# Step 3: Edit the copied file in your project
# Your project's .claude/skills/starter/SKILL.md will override the plugin's version
# Step 4: Commit to version control (optional)
git add .claude/
git commit -m "feat: customize bkit starter skill"| Component | Location | Description |
|---|---|---|
| Skills | ~/.claude/plugins/bkit/skills/ |
Domain knowledge, context and slash commands (e.g., /pdca plan) |
| Agents | ~/.claude/plugins/bkit/agents/ |
Specialized AI assistants |
| Templates | ~/.claude/plugins/bkit/templates/ |
Document templates |
| Scripts | ~/.claude/plugins/bkit/scripts/ |
Hook scripts |
| Config | ~/.claude/plugins/bkit/bkit.config.json |
Central configuration |
- Customized files don't receive plugin updates. When bkit is updated, your customized files remain unchanged while non-customized files are updated automatically.
- Check the CHANGELOG periodically for updates that might affect your customizations.
- Delete a customized file to revert to the plugin's default version.
- Attribution required: When creating derivative plugins, follow the License & Attribution guidelines.
/claude-code-learning/starter # Static website (Starter level)
/dynamic # Fullstack with BaaS (Dynamic level)
/enterprise # Microservices with K8s (Enterprise level)/pdca plan {feature} # Create plan document
/pdca design {feature} # Create design document
/pdca do {feature} # Implementation guide
/pdca analyze {feature} # Run gap analysis
/pdca iterate {feature} # Auto-fix with Evaluator-Optimizer pattern
/pdca report {feature} # Generate completion report
/pdca status # Check current PDCA status
/pdca next # Guide to next PDCA stepCTO-Led Agent Teams enable parallel PDCA execution with multiple AI agents orchestrated by a CTO lead agent.
# Start CTO Team for a feature
/pdca team {feature}
# Monitor team progress
/pdca team status
# Cleanup team resources
/pdca team cleanupHow it works:
- CTO lead agent (opus) analyzes the feature and selects the optimal team composition
- Teammates are spawned in parallel (Dynamic: 3, Enterprise: 5 agents)
- Each teammate handles a specific area (QA, frontend, backend, security, etc.)
- CTO orchestrates task assignment, progress monitoring, and result aggregation
- Team is cleaned up after work is complete
Requirements:
- Set environment variable:
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 - Claude Code v2.1.32+
Available Team Agents (5 new):
| Agent | Model | Role |
|---|---|---|
| cto-lead | opus | Team orchestration, PDCA workflow management |
| frontend-architect | sonnet | UI/UX design, component architecture |
| product-manager | sonnet | Requirements analysis, feature prioritization |
| qa-strategist | sonnet | Test strategy, quality metrics coordination |
| security-architect | opus | Vulnerability analysis, auth design review |
| Level | Description | Stack |
|---|---|---|
| Starter | Static websites, portfolios | HTML, CSS, JS |
| Dynamic | Fullstack applications | Next.js, BaaS |
| Enterprise | Microservices architecture | K8s, Terraform, MSA |
bkit is primarily designed for software development. However, some components can inspire structured workflows beyond coding:
| Component | Beyond Development Uses |
|---|---|
| PDCA Methodology | Project management, process improvement |
| Document Templates | Planning any structured project |
| Gap Analysis | Comparing any plan vs. actual outcome |
Note: For general writing, research, or non-technical tasks, plain Claude Code (without bkit) is better suited.
- CUSTOMIZATION-GUIDE.md - Complete guide to customizing bkit for your organization
- Platform-specific configuration paths (macOS, Linux, Windows, WSL)
- Component customization (agents, skills, commands, hooks, templates)
- License attribution requirements for derivative works
- bkit design philosophy and architecture decisions
- System Architecture - Plugin structure and trigger system overview
- Context Engineering - LLM context curation principles (v1.4.2)
- Core Mission & Philosophy - 3 core philosophies (Automation First, No Guessing, Docs=Code)
- AI-Native Principles - AI-Native development and 3 core competencies
- PDCA Methodology - PDCA cycle and 9-stage pipeline relationship
- Graph Index - Obsidian-optimized component graph
- Development Pipeline - 9-stage pipeline skill
- Skills Reference - 27 domain skills (Commands deprecated in v1.4.4)
- Agents Reference - 16 specialized agents (including 5 CTO Team agents)
- Active PDCA - Current plan/design/analysis documents
- Archive - Completed PDCA + legacy documents
- Changelog - Version history and release notes
The bkit-system/ documentation is optimized for Obsidian's Graph View:
- Open
bkit-system/as an Obsidian vault - Press
Ctrl/Cmd + Gto open Graph View - Explore component relationships visually
See bkit-system/README.md for detailed instructions.
bkit automatically detects your language from trigger keywords:
| Language | Trigger Keywords |
|---|---|
| English | static website, beginner, API design |
| Korean | 정적 웹, 초보자, API 설계 |
| Japanese | 静的サイト, 初心者, API設計 |
| Chinese | 静态网站, 初学者, API设计 |
| Spanish | sitio web estático, principiante |
| French | site web statique, débutant |
| German | statische Webseite, Anfänger |
| Italian | sito web statico, principiante |
Claude Code supports configuring your preferred response language through the language setting in your settings file.
| File | Scope | Git Tracked |
|---|---|---|
.claude/settings.local.json |
Project (personal) | No (gitignored) |
.claude/settings.json |
Project (shared) | Yes |
~/.claude/settings.json |
User (global) | N/A |
Add the language key to any settings file:
{
"language": "korean"
}| Language | Setting Value |
|---|---|
| English | "english" (default) |
| Korean | "korean" |
| Japanese | "japanese" |
| Chinese | "chinese" |
| Spanish | "spanish" |
| French | "french" |
| German | "german" |
| Italian | "italian" |
Note: Trigger keywords work in any language. The
languagesetting only affects Claude's response language.
We welcome contributions! Please see CONTRIBUTING.md for guidelines.
- Only
adminteam members can merge tomain - All changes require pull request review
- Version releases are managed through Git tags
Copyright 2024-2026 POPUP STUDIO PTE. LTD.
Licensed under the Apache License, Version 2.0. See LICENSE for details.
You must include the NOTICE file in any redistribution.
- Issues: GitHub Issues
- Email: contact@popupstudio.ai
Made with AI by POPUP STUDIO





