hats

v0.2.1+codex.20260928122426

Operating roles for the assistant you're already using: an overseer for agent work, a live QA companion, and a review closeout.

CodexClaude Code3 Skills

By kennykankushLicense: MIT0 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 3 skill or MCP entries
Source updated: Sep 28, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install hats for Codex and Claude Code

Installs for the current user

codex plugin marketplace add kennykankush/skillpack
codex plugin marketplace upgrade kennykankush-skillpack
codex plugin add hats@kennykankush-skillpack

Paste and run these commands in a terminal with Codex. They add and refresh the kennykankush-skillpack catalog, then install this plugin.

Compatibility: the page URL and API slug “hats” remain stable.

Codex: hats@agent-plugin-marketplace → hats@kennykankush-skillpack

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/kennykankush/skillpack

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/hats/.

Plugin files

plugins/hats/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/autoreview/SKILL.md
├── skills/birdwatch/SKILL.md
└── skills/overseer/SKILL.md

Included Skills3

autoreviewskills/autoreview/SKILL.md

Auto Review closeout. Codex review is the default when no engine is set and is the recommended reviewer.

birdwatchskills/birdwatch/SKILL.md

Live QA companion for product and dev sweeps, the live twin of gauntlet. Use when the user drives an app or flow and wants the agent to watch alongside: tail logs, verify UI against API and DB state, capture experience notes in the user's words, track discrepancies, or act as a scribe while they test.

overseerskills/overseer/SKILL.md

Control-tower role for agent work. Use when the user asks the assistant to watch or monitor what other coding agents or sessions are doing, check whether an agent's work is valid, relay decisions or questions to an agent on their behalf, keep them briefed across several agents, or keep a watch log while they are away. Gets ready on the whole project first, keeps provenance, and never turns the user's presence into permission.

Plugin manifests2

plugins/hats/.codex-plugin/plugin.json

{
  "name": "hats",
  "version": "0.2.1+codex.20260928122426",
  "description": "Operating roles for the assistant you're already using: an overseer for agent work, a live QA companion, and a review closeout.",
  "author": {
    "name": "kennykankush",
    "url": "https://github.com/kennykankush"
  },
  "homepage": "https://github.com/kennykankush/skillpack/tree/main/plugins/hats",
  "repository": "https://github.com/kennykankush/skillpack",
  "license": "MIT",
  "keywords": [
    "hats",
    "roles",
    "overseer",
    "agent-coordination",
    "review",
    "autoreview",
    "watcher",
    "qa",
    "observability",
    "codex",
    "claude"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Hats",
    "shortDescription": "Operating roles for the assistant you are already using.",
    "longDescription": "Portable operating roles. Overseer is a control tower for agent work: it gets ready on the whole project, watches other coding agents, checks their claims, relays the user's decisions without ever granting approvals, and keeps a watch log so the next overseer inherits the context. Birdwatch is the live QA companion: the user drives a flow while it verifies UI against API, DB and logs and records findings in the user's words. Autoreview runs a structured code-review closeout and verifies findings before fixes.",
    "developerName": "kennykankush",
    "category": "Productivity",
    "capabilities": [
      "Read",
      "Write"
    ],
    "websiteURL": "https://github.com/kennykankush/skillpack",
    "termsOfServiceURL": "https://github.com/kennykankush/skillpack/blob/main/LICENSE",
    "defaultPrompt": [
      "Oversee the other agents on this project and keep me briefed.",
      "Check whether the agent's latest work is valid.",
      "Tell the agent my decision and confirm it acknowledged.",
      "Use birdwatch while I test this app.",
      "Run autoreview on this branch before final."
    ],
    "brandColor": "#4C7D7A"
  }
}

plugins/hats/.claude-plugin/plugin.json

{
  "name": "hats",
  "version": "0.2.1",
  "description": "Operating roles for the assistant you're already using: an overseer for agent work, a live QA companion, and a review closeout.",
  "author": {
    "name": "kennykankush",
    "url": "https://github.com/kennykankush"
  },
  "homepage": "https://github.com/kennykankush/skillpack/tree/main/plugins/hats",
  "repository": "https://github.com/kennykankush/skillpack",
  "license": "MIT",
  "keywords": [
    "hats",
    "roles",
    "overseer",
    "agent-coordination",
    "review",
    "autoreview",
    "watcher",
    "qa",
    "observability",
    "codex",
    "claude"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[hats on Agent Plugins Marketplace](https://pluginsmp.com/plugins/hats)