Agent Plugins Marketplace
← All plugins

question-bench

v0.1.2

Benchmark review-plan question effectiveness via experiment-based ablation. Applies different question subsets to a plan (or directory of plans) in parallel experiments, evaluates each against fixed plan-quality questions (Q-PQ1..Q-PQ8), and compares quality spreads to identify which questions drive real improvement.

CodexClaude Code1 Skill

By whichguyLicense: MIT0 GitHub starsUpdated 4 days ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 20, 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 question-bench for Codex and Claude Code

Installs for the current user
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add question-bench@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. 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/whichguy/skill-craft

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

Plugin files

plugins/question-bench/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/question-bench/SKILL.md

Included Skills1

question-benchskills/question-bench/SKILL.md

Benchmark review-plan question effectiveness via experiment-based ablation. Applies different question subsets to a plan (or directory of plans) in parallel experiments, evaluates each against fixed plan-quality questions (Q-PQ1..Q-PQ8), and compares quality spreads to identify which questions drive real improvement. Core question: can a smaller set of questions achieve equivalent plan quality? Finds the minimal effective question set and recommends keep/merge/drop dispositions. Two modes: improve-only (no reference — did questions materially improve?) and A/B comparison (reference provided — how does question-derived planB compare?). Supports --dry-run for quick per-question verdict scan. AUTOMATICALLY INVOKE when user mentions: - "benchmark questions", "question effectiveness", "which questions matter" - "test review questions", "question impact", "question overlap" - "question bench", "bench questions", "ablation" NOT for: reviewing a plan (use /review-plan), comparing prompts (use /compare-prompts)

Plugin manifests2

plugins/question-bench/.codex-plugin/plugin.json
{
  "name": "question-bench",
  "version": "0.1.2",
  "description": "Benchmark review-plan question effectiveness via experiment-based ablation. Applies different question subsets to a plan (or directory of plans) in parallel experiments, evaluates each against fixed plan-quality questions (Q-PQ1..Q-PQ8), and compares quality spreads to identify which questions drive real improvement.",
  "author": {
    "name": "whichguy",
    "url": "https://github.com/whichguy"
  },
  "homepage": "https://github.com/whichguy/skill-craft",
  "repository": "https://github.com/whichguy/skill-craft",
  "license": "MIT",
  "keywords": [
    "skill-craft",
    "question-bench",
    "portable-skills",
    "prompt-only"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Question Bench",
    "shortDescription": "Benchmark review-plan question effectiveness via experiment-based ablation. Applies different question subsets to a…",
    "longDescription": "Benchmark review-plan question effectiveness via experiment-based ablation. Applies different question subsets to a plan (or directory of plans) in parallel experiments, evaluates each against fixed plan-quality questions (Q-PQ1..Q-PQ8), and compares quality spreads to identify which questions drive real improvement.",
    "developerName": "whichguy",
    "category": "Productivity",
    "capabilities": [
      "Read"
    ],
    "defaultPrompt": [
      "Use $question-bench:question-bench for this task."
    ]
  }
}
plugins/question-bench/.claude-plugin/plugin.json
{
  "name": "question-bench",
  "version": "0.1.2",
  "description": "Benchmark review-plan question effectiveness via experiment-based ablation. Applies different question subsets to a plan (or directory of plans) in parallel experiments, evaluates each against fixed plan-quality questions (Q-PQ1..Q-PQ8), and compares quality spreads to identify which questions drive real improvement.",
  "author": {
    "name": "whichguy",
    "url": "https://github.com/whichguy"
  },
  "homepage": "https://github.com/whichguy/skill-craft",
  "repository": "https://github.com/whichguy/skill-craft",
  "license": "MIT",
  "keywords": [
    "skill-craft",
    "question-bench",
    "portable-skills",
    "prompt-only"
  ]
}

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.

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