How do I install the Codex Guide skill?

Run npx skillmds@latest add xonovex/codex-guide in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Codex Guide safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Codex Guide?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Codex Guide free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Codex Guide?

xonovex (@xonovex) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Codex Guide by xonovex — Agent Skill

Name: Codex Guide
Author: xonovex

Codex Guide

Use when configuring Codex hooks, plugins, skills, config layers, or managed requirements. Triggers on hooks.json, config.toml, requirements.toml, SessionStart, PreToolUse, PermissionRequest, SubagentStart, Stop, plugin-bundled hooks, hook trust hashes, concurrent commands, skipped prompt/agent handlers, or Codex guardrail coverage, even when the user doesn't say 'Codex hook'.

xonovex ec3e7df 7 files · 20.0 KB Updated Sep 17, 2026

File contents

Codex Hooks and Guardrails

Configure Codex's native hooks and guardrails without inventing unsupported guarantees or a universal hook file.

Essentials

Probe the release - Record codex --version or an explicit not-installed result with the matrix snapshot.
Use command handlers - Only documented executing handler types can satisfy a capability.
Reject parsed-only support - Prompt, agent, and asynchronous command handlers are not executing release behavior in this snapshot.
Scope the guardrail - PreToolUse covers shell and unified exec, patch/edit/write, MCP, and most local function tools; hosted and specialized opt-out paths remain outside the guarantee.
Preserve trust layers - Non-managed definitions are hash-reviewed; managed hooks require separately distributed scripts.
Transact native config - Preview and verify hooks.json, config.toml, plugin, or requirements changes without replacing unrelated state.

Gotchas

Only type: command executes in the documented snapshot; prompt and agent handlers are parsed but skipped.
The async option is parsed but asynchronous command hooks are skipped.
PreToolUse is a partial guardrail because hosted tools and specialized paths that opt out of the local function-tool hook path are not intercepted.
Matching command hooks start concurrently, so a denial cannot prevent another matching hook from starting.
SubagentStart can add context, but continue: false does not stop the subagent from starting.

Example

Codex PreToolUse alone cannot block every privileged operation. Match covered shell/unified-exec calls as Bash, patch calls as apply_patch, Edit, or Write, MCP calls by their tool name, and other covered local function tools by function name. State that hosted tools and specialized opt-out paths remain uncovered.

Progressive Disclosure

Read references/capabilities.md - Load when mapping semantic intents to native events, handlers, guarantees, versions, ordering, context, or limitations
Read references/onboarding.md - Load when discovering, previewing, applying, verifying, disabling, rolling back, updating, or detecting drift
Read references/patterns.md - Load when translating deterministic hooks, model evaluators, specialist agents, or managed adoption recipes

---name: codex-guidedescription: Use when configuring Codex hooks, plugins, skills, config layers, or managed requirements. Triggers on hooks.json, config.toml, requirements.toml, SessionStart, PreToolUse, PermissionRequest, SubagentStart, Stop, plugin-bundled hooks, hook trust hashes, concurrent commands, skipped prompt/agent handlers, or Codex guardrail coverage, even when the user doesn't say 'Codex hook'.---# Codex Hooks and GuardrailsConfigure Codex's native hooks and guardrails without inventing unsupported guarantees or a universal hook file.## Essentials- **Probe the release** - Record `codex --version` or an explicit not-installed result with the matrix snapshot.- **Use command handlers** - Only documented executing handler types can satisfy a capability.- **Reject parsed-only support** - Prompt, agent, and asynchronous command handlers are not executing release behavior in this snapshot.- **Scope the guardrail** - `PreToolUse` covers shell and unified exec, patch/edit/write, MCP, and most local function tools; hosted and specialized opt-out paths remain outside the guarantee.- **Preserve trust layers** - Non-managed definitions are hash-reviewed; managed hooks require separately distributed scripts.- **Transact native config** - Preview and verify hooks.json, config.toml, plugin, or requirements changes without replacing unrelated state.## Gotchas- Only `type: command` executes in the documented snapshot; prompt and agent handlers are parsed but skipped.- The async option is parsed but asynchronous command hooks are skipped.- `PreToolUse` is a partial guardrail because hosted tools and specialized paths that opt out of the local function-tool hook path are not intercepted.- Matching command hooks start concurrently, so a denial cannot prevent another matching hook from starting.- `SubagentStart` can add context, but `continue: false` does not stop the subagent from starting.## ExampleCodex `PreToolUse` alone cannot block every privileged operation. Match covered shell/unified-exec calls as `Bash`, patch calls as `apply_patch`, `Edit`, or `Write`, MCP calls by their tool name, and other covered local function tools by function name. State that hosted tools and specialized opt-out paths remain uncovered.## Progressive Disclosure- Read [references/capabilities.md](references/capabilities.md) - Load when mapping semantic intents to native events, handlers, guarantees, versions, ordering, context, or limitations- Read [references/onboarding.md](references/onboarding.md) - Load when discovering, previewing, applying, verifying, disabling, rolling back, updating, or detecting drift- Read [references/patterns.md](references/patterns.md) - Load when translating deterministic hooks, model evaluators, specialist agents, or managed adoption recipes

Frequently asked questions