By pactkit
Spec-driven agentic DevOps toolkit — PDCA workflows, role-based agents, and behavioral governance for Claude Code
npx claudepluginhub pactkit/claude-code-plugin --plugin pactkitImplement code per Spec, strict TDD
QA verification: security scan, code quality scan, Spec alignment
Standalone requirement clarification before planning
Product design for greenfield projects: PRD generation, story decomposition, board setup
Code cleanup, Board update, Git commit
Hotfix fast track: lightweight fix path that bypasses PDCA
Initialize project scaffolding and governance structure
Analyze requirements, create Spec and Story
Push branch and create pull request via gh CLI
Version release: snapshot, archive, Git tag, and GitHub Release
Automated PDCA Sprint orchestration via Subagent Team (Slim Team)
Deep code analysis and execution tracing.
Product design and requirements decomposition for greenfield projects.
Quality assurance and Test Case owner.
Release engineering and housekeeping.
Security specialist (OWASP).
Implementation specialist focused on TDD.
High-level design and Intent Graph management.
Diagnostic expert.
System visualization specialist (Draw.io).
Cross-artifact consistency check: Spec ↔ Board ↔ Test Cases
Sprint Board atomic operations: add Story, update Task, archive completed Stories
Diagnose project health status
Generate Draw.io XML architecture diagrams
Version release: snapshot, archive, Git tag, and GitHub Release
PR Code Review with structured SOLID, security, and quality checklists
File scaffolding: create Spec, test files, E2E tests, Git branches, Skills
Project state overview for cold-start orientation
Deep code tracing and execution flow analysis
Generate project code dependency graph (Mermaid), supporting file-level, class-level, and function-level call chain analysis
Spec-driven agentic DevOps toolkit for Claude Code. This repository contains the plugin format distribution of PactKit.
PactKit compiles development workflows, role-based agents, and behavioral governance into executable "constitutions" and "playbooks" for Claude Code. It enforces a PDCA (Plan → Do → Check → Act) cycle with strict TDD, spec-driven development, and multi-agent orchestration.
Copy the pactkit-plugin/ directory into your project:
cp -r pactkit-plugin/.claude-plugin /path/to/your/project/
cp pactkit-plugin/CLAUDE.md /path/to/your/project/.claude/
cp -r pactkit-plugin/agents /path/to/your/project/.claude/
cp -r pactkit-plugin/commands /path/to/your/project/.claude/
cp -r pactkit-plugin/skills /path/to/your/project/.claude/
Install via pip and let PactKit deploy automatically:
pip install pactkit
pactkit init
See the main repository for full documentation.
| Directory | Contents | Count |
|---|---|---|
agents/ | Role-based AI agent definitions | 9 |
commands/ | PDCA command playbooks | 11 |
skills/ | Specialized skill modules | 10 |
CLAUDE.md | Global constitution (behavioral rules) | 1 |
| Command | Description |
|---|---|
/project-plan | Analyze requirements, create Spec and Story |
/project-act | Implement code per Spec with strict TDD |
/project-check | QA verification: security scan, code quality |
/project-done | Code cleanup, board update, Git commit |
/project-sprint | Automated PDCA orchestration via subagent team |
/project-hotfix | Lightweight fast-fix path |
/project-design | Greenfield product design and PRD generation |
/project-release | Version release: snapshot, archive, Git tag |
/project-pr | Push branch and create pull request |
/project-init | Initialize project scaffolding |
/project-clarify | Standalone requirement clarification |
| Agent | Role |
|---|---|
system-architect | High-level design and planning |
senior-developer | TDD implementation specialist |
qa-engineer | Quality assurance and test cases |
repo-maintainer | Release engineering and housekeeping |
product-designer | PRD and story decomposition |
code-explorer | Deep code analysis and tracing |
security-auditor | OWASP security review |
visual-architect | Draw.io diagram generation |
system-medic | Project health diagnostics |
MIT
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Uses power tools
Uses Bash, Write, or Edit tools
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.