nddev-codex-app

Start here for the nddev-builder toolkit. Indexes the Codex artifact families and the creator, checker, reviewer, and workflow skill that owns each, points at the single reference for schemas and current (Beta, experimental, or under-development) surfaces, and routes the task to the right skill. Use first whenever building, checking, reviewing, or releasing a Codex artifact, or when unsure which builder skill applies.

A guided first run of the nddev-builder toolkit — from zero to a working, checked Codex artifact in ordered steps. Use when new to nddev-builder, onboarding, or unsure which builder skill to start with.

Create or revise a Codex marketplace catalog with valid plugin sources, categories, installation policy, and authentication policy. Use when publishing local or remote plugin collections.

Check a managed Codex requirements.toml layer for supported keys, permission-profile consistency, and a valid lower-layer default. Use before delivering managed /etc/codex or MDM requirements.

Create a managed Codex requirements.toml layer that constrains permission profiles and other admin policy. Use when authoring the /etc/codex or MDM-delivered managed requirements a lower config layer must satisfy.

Install and iterate on a Codex plugin locally in developer mode: the install, reinstall, and cachebuster test loop for a plugin under development, run against an isolated install and never live state. Use when running or iterating on a plugin, its skills, MCP, hooks, or bundled app locally.

Version, catalog, and publish a native Codex plugin for distribution — the release step after dev-test, covering the SemVer manifest bump, marketplace catalog update, distribution source, and portal submission.

Build a whole Codex plugin from intent, not a single artifact. Define the product boundary, scaffold the manifest and every bundled capability (skills, hooks, MCP servers, apps) plus an optional personal marketplace entry, and validate the complete bundle. Use to compose a coherent multi-capability plugin rather than one standalone file.

Audit a complete plugin/marketplace bundle for release readiness, verifying cross-artifact identity, versioning, policy, presentation, and coherence across every bundled Codex artifact. Use as the pre-publish gate after per-artifact review, to prove the whole product is shippable rather than that individual files merely parse.

Check native Codex custom-agent TOML, role clarity, supported overrides, authority, and delegation behavior. Use before installing an agent or after changing its instructions, tools, model, or sandbox.

Create or revise native Codex custom subagent TOML with a narrow role, clear delegation contract, and intentional runtime controls. Use when adding repository or user agents for specialized parallel work.

Check native Codex .app.json names, developer-mode app ids, plugin linkage, authentication boundaries, and discovery. Use before bundling, installing, or changing app mappings.

Create or revise native Codex .app.json mappings with stable ChatGPT developer-mode app ids, plugin linkage, and clear authentication ownership. Use when a plugin exposes an app-backed connector to Codex.

Review a repository or directory containing Codex skills, plugins, marketplaces, agents, hooks, MCP, apps, config, instructions, or rules. Use for release readiness and cross-artifact quality audits.

Check Codex config.toml syntax, supported keys, precedence, safety-model consistency, paths, MCP transports, and runtime parsing. Use before installing or changing any Codex configuration layer.

Create or revise Codex config.toml layers with explicit model, safety, feature, project, and MCP settings. Use when adding a repository config, CODEX_HOME config, or setup overlay.

Check Codex hooks.json schemas, supported events, command references, timeouts, matchers, and failure behavior. Use before trusting, installing, or changing plugin-bundled lifecycle hooks.

Create or revise native Codex hooks.json events and command handlers with strict inputs, timeouts, portability, and failure behavior. Use when automating lifecycle checks around Codex sessions or tool calls.

Check AGENTS.md files for discovery, scope, precedence, contradictions, stale facts, executable commands, and native Codex boundaries. Use before merging instruction changes or diagnosing agent behavior.

Create or revise layered AGENTS.md instructions with clear scope, verified repository facts, native Codex boundaries, and concise operating rules. Use when adding project, directory, or global agent guidance.

Check Codex marketplace JSON, plugin identities and sources, categories, policies, and reachable local plugins. Use before marketplace registration, publication, or catalog updates.

Check Codex MCP JSON or TOML definitions, transport completeness, launcher provenance, environment handling, and runtime connectivity. Use before enabling, bundling, or releasing an MCP server.

Create or revise native Codex MCP definitions for stdio or HTTP servers with complete transport metadata, clear authentication, and pinned launchers. Use when exposing tools through a plugin or config.

Check a native Codex plugin manifest, bundled capability paths, policies, and nested artifacts. Use before marketplace publication, installation, version bumps, or plugin releases.

Create or revise native Codex plugins with valid manifests and intentionally bundled skills, apps, MCP servers, or hooks. Use when building a distributable Codex plugin rather than standalone files.

Check native Codex execpolicy .rules syntax, command-prefix scope, overlap, bypasses, and positive and negative examples. Use before installing rules or changing shell-command approval policy.

Create or revise native Codex execpolicy .rules files with narrow command prefixes, explicit decisions, and executable positive and negative examples. Use when governing shell-command approval behavior.

Check native Codex skill directories, SKILL.md routing metadata, OpenAI UI metadata, and referenced resources. Use before publishing, installing, or changing any Codex skill.

Create or revise native Codex skills with precise routing, progressive disclosure, reusable resources, and OpenAI UI metadata. Use when adding a SKILL.md workflow or improving an existing skill.