Agent Plugins Marketplace
← All plugins

kit

v3.0.0

A Claude Code kit with two roles that grade opposite halves of the same round. The MENTOR coaches how each request was framed before the work runs, then grades the ask — framing, leverage, learnings applied. The CRITIC judges, in fresh context and its own words, whether the thing you ASKED for actually happened, then grades the delivery — did it happen, was there evidence, did it stay in scope. Both write to one append-only ledger per repo, and the SCORECARD renders it as a published board where the human prompter and the model are scored side by side.

Claude Code3 Skills

0 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
3 skill or MCP entries
Source updated
Sep 22, 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 kit for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install kit-3@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

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/wyattroy/claude-kit

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

Plugin files

plugins/kit/
├── .claude-plugin/plugin.json
├── skills/critic/SKILL.md
├── skills/mentor/SKILL.md
└── skills/scorecard/SKILL.md

Included Skills3

criticskills/critic/SKILL.md

Show finished work to a fresh Critic before showing it to the user. Use after any real work — something built, fixed, measured or shipped — to judge whether the thing they ASKED for actually happened, and to grade the delivery into the repo's scorecard. Not after a question answered or a file handed over.

mentorskills/mentor/SKILL.md

A standing Claude Code mentor — coaches how the user frames work requests, inline, before the work executes, and GRADES each ask into the repo's scorecard. Use this at the START of any substantive work request in a coding or project session, even when they don't mention coaching: open the reply with a short Mentor note on their framing, record the grade, then do the work. Also use whenever they ask how to use Claude Code better, how to phrase or structure a request, whether to split a session, plan first, use subagents or background agents, or how they are scoring. Skip only for trivial messages (a bare yes, a ship-it, a question back).

scorecardskills/scorecard/SKILL.md

Show the gamified scorecard — how well the user is asking, how well Claude is delivering, both scored out of 100 with XP, levels, streaks and badges. Use when they ask how they are doing, how their prompting is scoring, what their level or streak is, to see or refresh the dashboard, or after a mentor or critic grade has been written and the board is now out of date.

Plugin manifests1

plugins/kit/.claude-plugin/plugin.json
{
  "name": "kit",
  "version": "3.0.0",
  "description": "A Claude Code kit with two roles that grade opposite halves of the same round. The MENTOR coaches how each request was framed before the work runs, then grades the ask — framing, leverage, learnings applied. The CRITIC judges, in fresh context and its own words, whether the thing you ASKED for actually happened, then grades the delivery — did it happen, was there evidence, did it stay in scope. Both write to one append-only ledger per repo, and the SCORECARD renders it as a published board where the human prompter and the model are scored side by side.",
  "keywords": [
    "mentor",
    "coaching",
    "review",
    "verification",
    "scorecard",
    "gamification",
    "prompting"
  ]
}

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.

[kit on Agent Plugins Marketplace](https://pluginsmp.com/plugins/kit-3)