ask-me-again

v0.1.0

Re-asks an agent's open questions one at a time, in one fixed shape, with every recommended fix checked first.

CodexClaude Code1 Skill

By Patrick D'appollonioLicense: MIT8 GitHub starsUpdated last week

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 17, 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 ask-me-again for Codex and Claude Code

Installs for the current user

codex plugin marketplace add patrickdappollonio/claude-plugins
codex plugin marketplace upgrade patrickdappollonio
codex plugin add ask-me-again@patrickdappollonio

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

Compatibility: the page URL and API slug “ask-me-again” remain stable.

Codex: ask-me-again@agent-plugin-marketplace → ask-me-again@patrickdappollonio

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/patrickdappollonio/claude-plugins

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

Plugin files

plugins/ask-me-again/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/ask-me-again/SKILL.md

Included Skills1

ask-me-againskills/ask-me-again/SKILL.md

Use when the user says "/ask-me-again", "ask me again", "ask me that properly", or "one question at a time". Also use when the user says the agent's questions were unclear, too technical, too many at once, "a wall of text", or squeezed into a multiple-choice prompt with no room for context. The skill takes every question the agent has open. It checks the facts behind each one, and it checks that each recommended fix really works. Then it asks the questions again in plain chat, one per message, in one fixed shape - a numbered heading that states the claim, the situation, a numbered flow to the consequence, the fix, its cost, and your call. Only a direct answer (apply, reject, or a different direction) closes a question. After a doubtful or vague reply, the agent asks the user to say which they mean. It builds nothing until the last question is closed.

Plugin manifests2

plugins/ask-me-again/.codex-plugin/plugin.json

{
  "name": "ask-me-again",
  "version": "0.1.0",
  "description": "Re-asks an agent's open questions one at a time, in one fixed shape, with every recommended fix checked first.",
  "author": {
    "name": "Patrick D'appollonio",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/patrickdappollonio/claude-plugins/tree/main/plugins/ask-me-again",
  "license": "MIT",
  "keywords": [
    "questions",
    "decisions",
    "clarification",
    "communication",
    "plain-language",
    "one-at-a-time"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Ask Me Again",
    "shortDescription": "Re-ask open questions one at a time, in a clear shape.",
    "longDescription": "Takes every question the agent has open, checks the facts behind each and that each recommended fix works, then asks them again in plain chat, one per message: a numbered claim, the situation, a numbered flow to the consequence, the fix, its cost, and your call. Only a direct apply, reject, or different direction closes a question. After a doubtful reply it asks the user to say which they mean, and it builds nothing until the last question is closed.",
    "developerName": "Patrick D'appollonio",
    "category": "Productivity",
    "capabilities": [
      "Explain"
    ],
    "defaultPrompt": [
      "Ask me again."
    ]
  }
}

plugins/ask-me-again/.claude-plugin/plugin.json

{
  "name": "ask-me-again",
  "description": "Re-asks the questions an agent has open, one per chat message, in one fixed shape — a numbered claim, the situation, a numbered flow to the consequence, the fix, its cost, your call — after checking the facts and that each recommended fix really works, and builds nothing until every question has a direct apply, reject, or different direction. After a doubtful reply it asks the user to say which they mean. Never uses the harness question tool.",
  "version": "0.1.0",
  "author": {
    "name": "Patrick D'appollonio",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/patrickdappollonio/claude-plugins/tree/main/plugins/ask-me-again",
  "license": "MIT",
  "keywords": [
    "questions",
    "decisions",
    "clarification",
    "communication",
    "plain-language",
    "one-at-a-time"
  ]
}