npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@bryanofearth/claude-agent-kit

v1.2.0

Published

A CLI tool and npm package that distributes curated Claude Code agents, slash commands, skills, and hooks to enhance developer productivity

Readme

Lean Agile Team — Claude Code Plugin

Ship fast, learn faster. 6 agents, 10 skills, Agent Teams coordination.

Prerequisites

  • Claude Code installed
  • Required for full coordination: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 (set automatically by this plugin's settings.json)
  • Works without Agent Teams in degraded sequential mode via Task() fallback

Quick Start

# Install the plugin (from GitHub)
claude plugin add github:bryanweaver/claude-agent-kit

# Or load locally during development
# claude --plugin-dir /path/to/agent-orchestration-system

# Ship a feature
/team-ship add user authentication

# Fix a production bug
/team-fix users can't log in

# Clean up tech debt
/team-cleanup authentication module

# Run and fix tests
/team-run-tests

# Add critical test coverage
/team-add-tests payment processing

Architecture

┌─────────────────────────────────────────────────┐
│                  Team Lead                       │
│            (Claude Code Main Agent)              │
└──────────────────┬──────────────────────────────┘
                   │
        ┌──────────┼──────────┬──────────┐
        │          │          │          │
        ▼          ▼          ▼          ▼
  ┌──────────┐ ┌────────┐ ┌──────────┐ ┌────────────┐
  │Full Stack│ │Database│ │ Reviewer │ │ Documentor │
  │Developer │ │ Admin  │ │          │ │            │
  └──────────┘ └────────┘ └──────────┘ └────────────┘
        │          │          │          │
        └──────────┼──────────┼──────────┘
                   │
                   ▼
            ┌──────────┐
            │ Shipper  │
            │ (Pipeline│
            │  Owner)  │
            └──────────┘
                   │
                   ▼
         Shared Task List
    (Agent Teams coordination)

The Lean Team

| Agent | Role | Model | Key Traits | |-------|------|-------|------------| | Full Stack Developer | Rapid implementation across entire stack | Sonnet | Worktree isolation, project memory | | Database Admin | Schema, queries, migrations, data integrity | Sonnet | Worktree isolation, project memory | | Shipper | Git, testing, building, deployment, PRs | Sonnet | Unblocked pipeline access | | Reviewer | Security, bugs, performance review | Sonnet | Read-only (plan mode) | | Documentor | Create, maintain, organize codebase docs | Sonnet | Runs after tests pass | | Meta-Agent | Generate new custom agents | Opus | On-demand agent creation |

Skills

Workflow Skills

| Skill | Purpose | Speed | |-------|---------|-------| | /team-ship <feature> | Feature branch → implement → review → test → deploy → PR | Balanced | | /team-fix <bug> | Hotfix → diagnose → patch → deploy (no review step) | Fastest | | /team-cleanup <area> | Analyze tech debt → refactor → validate | Thorough | | /team-run-tests [scope] | Run all tests → batch-fix failures → verify | Thorough | | /team-add-tests <area> | Identify critical gaps → write minimal tests | Focused |

Utility Skills

| Skill | Purpose | |-------|---------| | /team-init-docs [area] | Generate comprehensive codebase documentation | | /team-update-docs [changes] | Update docs to reflect recent code changes | | /team-create-agent <description> | Create a new custom agent via meta-agent | | /team-repo-status [focus] | Repository health report (git, todos, activity) | | /team-all-tools | List all available tools with signatures |

Workflow Details

/team-ship — Build and Deploy Features

Shipper ──► Full Stack Dev + DB Admin (parallel) ──► Shipper ──► Reviewer ──► Shipper ──► Documentor ──► Shipper
Branch       Implement feature                       Commit       Review       Test         Update Docs    Deploy+PR

Tasks: Create branch → Implement → Commit → Review → Test → Fix regressions (if needed) → Update docs → Deploy & PR

/team-fix — Emergency Bug Fixes

Shipper ──► Full Stack Dev + DB Admin ──► Shipper ──► Shipper ──► Documentor ──► Shipper
Hotfix       Diagnose & patch              Commit      Test+Deploy  Update Docs    Merge

No reviewer step — speed is the priority for emergencies.

/team-cleanup — Technical Debt

Shipper ──► Reviewer ──► Full Stack Dev + DB Admin (parallel) ──► Shipper ──► Shipper ──► Documentor ──► Shipper
Branch       Analyze       Refactor                                Commit      Test         Update Docs     PR

Reviewer-first: analyze before refactoring.

/team-run-tests — Batch Test and Fix

Shipper ──► Shipper ──► Full Stack Dev + DB Admin ──► Shipper ──► Shipper ──► Reviewer ──► Documentor ──► Shipper
Branch       Run tests    Fix failures (parallel)      Commit      Re-test     Review       Update Docs     PR
                              ↑                                       │
                              └───────── loop if still failing ───────┘

/team-add-tests — Critical Test Coverage

Shipper ──► Reviewer ──► Full Stack Dev + DB Admin (parallel) ──► Shipper ──► Documentor ──► Shipper
Branch       Find gaps     Write minimal tests                     Run tests    Update Docs    Commit+PR

Test the 20% that prevents 80% of disasters.

Plugin Structure

agent-orchestration-system/
├── .claude-plugin/
│   └── plugin.json              # Plugin manifest
├── agents/
│   ├── full-stack-developer.md  # Rapid full-stack implementation
│   ├── database-admin.md        # Database and data layer
│   ├── shipper.md               # Pipeline: git, test, build, deploy
│   ├── reviewer.md              # Security, bugs, performance review
│   ├── documentor.md            # Documentation creation and maintenance
│   └── meta-agent.md            # Agent generator
├── skills/
│   ├── team-ship/SKILL.md            # Feature development workflow
│   ├── team-fix/SKILL.md             # Emergency hotfix workflow
│   ├── team-cleanup/SKILL.md         # Tech debt refactoring workflow
│   ├── team-run-tests/SKILL.md        # Batch test and fix workflow
│   ├── team-add-tests/SKILL.md       # Critical test coverage workflow
│   ├── team-init-docs/SKILL.md       # Full documentation generation
│   ├── team-update-docs/SKILL.md     # Documentation maintenance
│   ├── team-create-agent/SKILL.md    # Custom agent creation
│   ├── team-repo-status/SKILL.md     # Repository health report
│   └── team-all-tools/SKILL.md       # List available tools
├── hooks/
│   └── hooks.json               # Quality gates and observability
├── settings.json                # Plugin settings (Agent Teams flag)
├── docs/
│   └── lean-agile-system.md     # Detailed system specification
└── .claude/
    └── settings.json            # Claude Code project settings

Configuration

Settings

The plugin automatically enables Agent Teams via settings.json:

{
  "env": {
    "CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
  }
}

Hooks

Three hooks provide quality gates and observability:

| Hook | Type | Purpose | |------|------|---------| | TaskCompleted | Prompt | LLM verifies task is genuinely complete before marking done | | TeammateIdle | Command | Logs idle events to <tmpdir>/lean-agile-team.log | | SubagentStop | Prompt | Validates git state is clean when shipper finishes (scoped via agent_name matcher) |

Dual-Mode Operation

Every skill supports two execution modes:

Agent Teams Mode (recommended)

With CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1:

  • Spawns real teammates that work in parallel
  • Uses shared task lists with dependency tracking
  • Teammates communicate via mailbox protocol
  • Full parallelism where workflows allow

Sequential Fallback

Without Agent Teams:

  • Executes agents sequentially via Task() calls
  • Same workflow steps, same quality gates
  • Works on any Claude Code version
  • Slightly slower due to serial execution

Creating Custom Agents

Use the meta-agent to generate new agents:

/team-create-agent Create a new agent that handles API integration testing

The meta-agent will:

  1. Analyze your requirements
  2. Select appropriate tools and model
  3. Generate a complete agent definition
  4. Save to agents/<name>.md

Key Principles

  • Ship fast, learn faster — working software over perfect software
  • Minimal testing — test the 20% that prevents 80% of disasters
  • Speed focus/team-fix is fastest, /team-ship is balanced, /team-cleanup and /team-run-tests are thorough
  • Non-blocking reviews — reviewer suggestions don't stop deployment (except security)
  • Clean pipeline — shipper owns the entire git-to-production flow
  • Quality without bureaucracy — pragmatic reviews, not nitpicks