plugin-creator

por openai

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can…

npx skills add https://github.com/openai/plugins --skill plugin-creator

Plugin Creator

Quick Start

  1. Run the scaffold script:
  # Plugin names are normalized to lower-case hyphen-case and must be <= 64 chars.
  # The generated folder and plugin.json name are always the same.
# Run from repo root (or replace .agents/... with the absolute path to this SKILL).
# By default creates in ~/plugins/<plugin-name>.
python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py <plugin-name>
  1. Open <plugin-path>/.codex-plugin/plugin.json and replace [TODO: ...] placeholders.

  2. Generate or update the personal marketplace entry when the plugin should appear in Codex UI ordering:

# Personal marketplace entries default to ~/.agents/plugins/marketplace.json.
python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py my-plugin --with-marketplace

If the current Git repo already has .agents/plugins/marketplace.json and the user has not said whether the plugin is personal or shared with their team, ask before generating a marketplace entry. When they choose the repo marketplace, use:

python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py my-plugin \
  --path ./plugins \
  --marketplace-path ./.agents/plugins/marketplace.json \
  --with-marketplace
  1. Generate/adjust optional companion folders as needed:
python3 .agents/skills/plugin-creator/scripts/create_basic_plugin.py my-plugin \
  --path <parent-plugin-directory> \
  --marketplace-path <marketplace-json-path> \
  --with-skills --with-hooks --with-scripts --with-assets --with-mcp --with-apps --with-marketplace

<parent-plugin-directory> is the directory where the plugin folder <plugin-name> will be created (for example ~/code/plugins).

What this skill creates

  • Default marketplace-backed scaffolds are personal: ~/plugins/<plugin-name>/ plus ~/.agents/plugins/marketplace.json.
  • If the current Git repo already has .agents/plugins/marketplace.json and the user has not said personal vs team, ask which marketplace to update before generating a marketplace entry.
  • Creates plugin root at /<parent-plugin-directory>/<plugin-name>/.
  • Always creates /<parent-plugin-directory>/<plugin-name>/.codex-plugin/plugin.json.
  • Fills the manifest with the full schema shape, placeholder values, and the complete interface section.
  • Creates or updates the selected marketplace when --with-marketplace is set.
    • If the marketplace file does not exist yet, seed top-level name plus interface.displayName placeholders before adding the first plugin entry.
  • <plugin-name> is normalized using skill-creator naming rules:
    • My Plugin → my-plugin
    • My--Plugin → my-plugin
    • underscores, spaces, and punctuation are converted to -
    • result is lower-case hyphen-delimited with consecutive hyphens collapsed
  • Supports optional creation of:
    • skills/
    • hooks/
    • scripts/
    • assets/
    • .mcp.json
    • .app.json

Marketplace workflow

  • Personal plugins use ~/.agents/plugins/marketplace.json.
  • Repo/team plugins use <repo-root>/.agents/plugins/marketplace.json.
  • Marketplace root metadata supports top-level name plus optional interface.displayName.
  • Treat plugin order in plugins[] as render order in Codex. Append new entries unless a user explicitly asks to reorder the list.
  • displayName belongs inside the marketplace interface object, not individual plugins[] entries.
  • Each generated marketplace entry must include all of:
    • policy.installation
    • policy.authentication
    • category
  • Default new entries to:
    • policy.installation: "AVAILABLE"
    • policy.authentication: "ON_INSTALL"
  • Override defaults only when the user explicitly specifies another allowed value.
  • Allowed policy.installation values:
    • NOT_AVAILABLE
    • AVAILABLE
    • INSTALLED_BY_DEFAULT
  • Allowed policy.authentication values:
    • ON_INSTALL
    • ON_USE
  • Treat policy.products as an override. Omit it unless the user explicitly requests product gating.
  • The generated plugin entry shape is:
{
  "name": "plugin-name",
  "source": {
    "source": "local",
    "path": "./plugins/plugin-name"
  },
  "policy": {
    "installation": "AVAILABLE",
    "authentication": "ON_INSTALL"
  },
  "category": "Productivity"
}
  • Use --force only when intentionally replacing an existing marketplace entry for the same plugin name.

  • If the selected marketplace file does not exist yet, create it with top-level "name", an "interface" object containing "displayName", and a plugins array, then add the new entry.

  • For a brand-new marketplace file, the root object should look like:

{
  "name": "[TODO: marketplace-name]",
  "interface": {
    "displayName": "[TODO: Marketplace Display Name]"
  },
  "plugins": [
    {
      "name": "plugin-name",
      "source": {
        "source": "local",
        "path": "./plugins/plugin-name"
      },
      "policy": {
        "installation": "AVAILABLE",
        "authentication": "ON_INSTALL"
      },
      "category": "Productivity"
    }
  ]
}

Required behavior

  • Outer folder name and plugin.json "name" are always the same normalized plugin name.
  • Do not remove required structure; keep .codex-plugin/plugin.json present.
  • Keep manifest values as placeholders until a human or follow-up step explicitly fills them.
  • If creating files inside an existing plugin path, use --force only when overwrite is intentional.
  • Preserve any existing marketplace interface.displayName.
  • When generating marketplace entries, always write policy.installation, policy.authentication, and category even if their values are defaults.
  • Add policy.products only when the user explicitly asks for that override.
  • Keep marketplace source.path relative to the selected marketplace root as ./plugins/<plugin-name>.
  • When the workflow created or updated a marketplace-backed plugin, end the final user-facing response with a short Codex app handoff. Say To view this in the Codex app: and write View <normalized plugin name> and Share <normalized plugin name> as Markdown links, not raw URLs or code spans.
  • The View deeplink uses codex://plugins/<normalized plugin name>?marketplacePath=<absolute marketplace.json path>. The Share deeplink uses the same URL with &mode=share.
  • Replace the placeholders with the real normalized plugin name and absolute marketplace.json path from the scaffolded plugin. URL-encode the path segment and query value when needed.
  • Do not add pluginName or hostId query parameters to these deeplinks. Codex derives both after the user clicks the link.
  • Do not emit the View <normalized plugin name> or Share <normalized plugin name> links when no marketplace entry was created or updated.

Reference to exact spec sample

For the exact canonical sample JSON for both plugin manifests and marketplace entries, use:

  • references/plugin-json-spec.md

Validation

After editing SKILL.md, run:

python3 <path-to-skill-creator>/scripts/quick_validate.py .agents/skills/plugin-creator

Más skills de openai

release
openai
Realizar un lanzamiento de Symphony incrementando la versión confirmada, integrándola, etiquetando el commit fusionado y verificando el flujo de trabajo de lanzamiento de Burrito. Usar cuando se solicite…
signing-entitlements
openai
Inspeccionar problemas de firma, entitlements, runtime reforzado y Gatekeeper en aplicaciones de macOS. Usar cuando se solicite diagnosticar fallos de firma de código, entitlements faltantes,…
building-ai-agent-on-cloudflare
openai
Crea agentes de IA en Cloudflare usando el Agents SDK con gestión de estado, WebSockets en tiempo real, tareas programadas, integración de herramientas y chat…
epigraphdb-skill
openai
Envía solicitudes compactas a la API de EpiGraphDB para ontología, literatura, MR, genes-fármacos y evidencia de vías de soporte. Úsalo cuando un usuario desee resúmenes concisos de EpiGraphDB.
runtime-behavior-probe
openai
Planificar y ejecutar investigaciones de comportamiento en tiempo de ejecución con scripts de sonda temporales, matrices de validación, controles de estado e informes centrados en hallazgos. Usar solo cuando…
deep-security-scan
openai
Úsalo cuando el usuario solicite un escaneo de seguridad de Codex profundo, exhaustivo, de múltiples pasadas o que reduzca la varianza, en todo el repositorio o en una ruta específica. Ejecuta pasadas independientes repetidas…
define-security-policy
openai
Definir, revisar o actualizar la guía de SECURITY.md para un repositorio o componente. Úselo cuando el usuario quiera aclarar qué debe revisar Codex Security, qué está fuera de…
validation
openai
Usar cuando Codex ya está en la fase de validación de un escaneo de seguridad o el usuario solicita explícitamente determinar si uno o más posibles hallazgos de seguridad…