Agent Plugins Marketplace
All plugins

prove

vdc9e67a

Adversarial verification skill: prover vs disprover agents argue, then a judge synthesizes a verdict

Claude Code1 Skill

0 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 6, 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 prove 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 prove@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/HollandDM/my-skills

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

Plugin files

prove/
├── .claude-plugin/plugin.json
└── skills/prove/SKILL.md

Included Skills1

proveskills/prove/SKILL.md

Prove or disprove claim about code, architecture, behavior, or technical property. Spawns adversarial agents — provers and disprovers — argue from multiple angles, synthesizes verdict. If undecided, enters combat loop where agents attack each other's arguments until resolved. Use when user says "prove", "verify", "does this guarantee", "is it always true that", "can this ever fail", "show me this holds", or asks whether something satisfies property. Works for code properties (null-safety, termination, invariants), architectural claims ("this migration is backward-compatible"), runtime behavior ("this endpoint never takes >5s"), design reasoning ("this approach scales"), or any assertion user wants rigorously examined.

Plugin manifests1

prove/.claude-plugin/plugin.json
{
  "name": "prove",
  "description": "Adversarial verification skill: prover vs disprover agents argue, then a judge synthesizes a verdict",
  "version": "dc9e67a"
}

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

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