claude-code-plugin
agent
Warn
Health Warn
- No license — Repository has no license file
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 5 GitHub stars
Code Pass
- Code scan — Scanned 9 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
Purpose
This tool provides a spec-driven, agentic DevOps toolkit for Claude Code. It enforces a structured Plan → Do → Check → Act (PDCA) development cycle by injecting custom AI agent definitions, commands, and skills directly into your project.
Security Assessment
Overall risk: Low. The automated code scan of 9 files found no dangerous patterns, hardcoded secrets, or requested dangerous permissions. The plugin operates primarily by copying text-based agent instructions and CLAUDE.md configuration files into your project's local directory. Because it is designed to orchestrate developer workflows, the underlying tool it helps manage will likely execute shell commands and access local files, but the plugin itself acts simply as a prompt and rule framework. No hidden network requests or malicious data harvesting were detected.
Quality Assessment
Quality is mixed but actively maintained. The project was updated very recently (pushed 0 days ago), demonstrating active development. However, there are significant concerns regarding its maturity and legal standing. Despite mentioning "MIT" at the bottom of the README, the automated scan flagged that the repository actually lacks a formal license file. Additionally, it suffers from extremely low community visibility with only 5 GitHub stars, meaning the codebase has undergone minimal public scrutiny.
Verdict
Use with caution — while the code itself appears safe and free of malicious payloads, the lack of a formal license file and very low community adoption mean it currently lacks proven legal and community trust.
This tool provides a spec-driven, agentic DevOps toolkit for Claude Code. It enforces a structured Plan → Do → Check → Act (PDCA) development cycle by injecting custom AI agent definitions, commands, and skills directly into your project.
Security Assessment
Overall risk: Low. The automated code scan of 9 files found no dangerous patterns, hardcoded secrets, or requested dangerous permissions. The plugin operates primarily by copying text-based agent instructions and CLAUDE.md configuration files into your project's local directory. Because it is designed to orchestrate developer workflows, the underlying tool it helps manage will likely execute shell commands and access local files, but the plugin itself acts simply as a prompt and rule framework. No hidden network requests or malicious data harvesting were detected.
Quality Assessment
Quality is mixed but actively maintained. The project was updated very recently (pushed 0 days ago), demonstrating active development. However, there are significant concerns regarding its maturity and legal standing. Despite mentioning "MIT" at the bottom of the README, the automated scan flagged that the repository actually lacks a formal license file. Additionally, it suffers from extremely low community visibility with only 5 GitHub stars, meaning the codebase has undergone minimal public scrutiny.
Verdict
Use with caution — while the code itself appears safe and free of malicious payloads, the lack of a formal license file and very low community adoption mean it currently lacks proven legal and community trust.
PactKit plugin for Claude Code — install via /plugin marketplace add pactkit/claude-code-plugin
README.md
PactKit — Claude Code Plugin
Spec-driven agentic DevOps toolkit for Claude Code. This repository contains the plugin format distribution of PactKit.
What is 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.
Installation
Option A: Claude Code Plugin (this repo)
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/
Option B: PyPI (recommended)
Install via pip and let PactKit deploy automatically:
pip install pactkit
pactkit init
See the main repository for full documentation.
What's Included
| 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 |
Commands
| 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 |
Agents
| 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 |
Links
License
MIT
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found