# Kagan

> Use this tool when you need to manage and execute coding tasks on codebases with autonomous or interactive agents. It solves problems of code automation, pair programming, and task management by providing a TUI-based Kanban board that assigns tasks to agents from 14 providers. With a web dashboard for remote access, it takes in codebase inputs and outputs executed tasks, making it ideal for development teams and coding projects.

Canonical page: https://skillsregistry.net/skills/gh-kagan-sh-kagan  
JSON: https://api.skillsregistry.net/v1/skills/gh-kagan-sh-kagan

## Description

Provides a TUI-based Kanban board for managing and running coding agents on codebases. Tasks are created and assigned to agents that execute autonomously or in interactive pair mode. Supports 14 agent providers including Claude, Codex, and Gemini with a web dashboard for remote access. Built with Python and Textual, featuring evaluation frameworks, documentation generation via MkDocs, and Cloudflare Workers integration.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gh-kagan-sh-kagan)
- **Repository:** <https://github.com/kagan-sh/kagan>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "gh-kagan-sh-kagan"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gh-kagan-sh-kagan` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gh-kagan-sh-kagan/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt