Agent Plugins Marketplace
← All plugins

prompt-builder

A prompt that works in chat often fails in production, and there is no way to tell whether an edit made it better or worse. Prompt-builder classifies the prompt, diagnoses its top failure modes, rewrites it on a 6-part stack calibrated to model tier and deployment, and scores it on five dimensions. You ship prompts with a number attached and catch regressions before your users do.

CodexClaude Code1 Skill

By Tyrone RossLicense: Apache-2.00 GitHub starsUpdated 3 weeks ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 24, 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 prompt-builder 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 prompt-builder@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/tyroneross/prompt-builder

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

Plugin files

prompt-builder/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/prompt-builder/SKILL.md

Included Skills1

prompt-builderskills/prompt-builder/SKILL.md

Use to create, rewrite, score, or A/B compare prompts calibrated to model tier (frontier/mid/small) and deployment (RAG, agent, eval judge). Triggers on "optimize this prompt", "system prompt". Callable by other agents.

Plugin manifests2

.codex-plugin/plugin.json
{
  "name": "prompt-builder",
  "description": "A prompt that works in chat often fails in production, and there is no way to tell whether an edit made it better or worse. Prompt-builder classifies the prompt, diagnoses its top failure modes, rewrites it on a 6-part stack calibrated to model tier and deployment, and scores it on five dimensions. You ship prompts with a number attached and catch regressions before your users do.",
  "author": {
    "name": "Tyrone Ross",
    "url": "https://github.com/tyroneross"
  },
  "license": "Apache-2.0",
  "keywords": [
    "prompt",
    "prompt-engineering",
    "optimization",
    "rag",
    "agents",
    "evals",
    "llm"
  ],
  "skills": "./skills",
  "interface": {
    "displayName": "Prompt Builder",
    "shortDescription": "A prompt that works in chat often fails in production. Prompt-builder diagnoses, rewrites, and scores it for your model tier and deployment, so you ship with a score and catch regressions early.",
    "longDescription": "A prompt that works in chat often fails in production, and there is no way to tell whether an edit made it better or worse. Prompt-builder classifies the prompt, diagnoses its top failure modes, rewrites it on a 6-part stack calibrated to model tier and deployment, and scores it on five dimensions. You ship prompts with a number attached and catch regressions before your users do.",
    "developerName": "Ross Labs",
    "category": "Coding",
    "capabilities": [
      "Read",
      "Write"
    ]
  },
  "repository": "https://github.com/tyroneross/prompt-builder",
  "homepage": "https://github.com/tyroneross/prompt-builder"
}
.claude-plugin/plugin.json
{
  "name": "prompt-builder",
  "description": "A prompt that works in chat often fails in production, and there is no way to tell whether an edit made it better or worse. Prompt-builder classifies the prompt, diagnoses its top failure modes, rewrites it on a 6-part stack calibrated to model tier and deployment, and scores it on five dimensions. You ship prompts with a number attached and catch regressions before your users do.",
  "author": {
    "name": "Tyrone Ross",
    "url": "https://github.com/tyroneross"
  },
  "license": "Apache-2.0",
  "keywords": [
    "prompt",
    "prompt-engineering",
    "optimization",
    "rag",
    "agents",
    "evals",
    "llm"
  ],
  "repository": "https://github.com/tyroneross/prompt-builder",
  "homepage": "https://github.com/tyroneross/prompt-builder"
}

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.

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