How do I install the Codex Config skill?

Run npx skillmds@latest add tomevault-io/codex-config 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 Config safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Codex Config?

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 Config free to use?

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

Who published Codex Config?

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

Codex Config by tomevault-io — Agent Skill

Name: Codex Config
Author: tomevault-io

File contents

Codex Configuration Management

Manages configuration files for OpenAI Codex CLI, including model settings, sandbox policies, MCP servers, and profiles.

Configuration Location

Primary Config: ~/.codex/config.toml

Skills Paths (precedence, highest first):

$CWD/.codex/skills/ - Current directory
$CWD/../.codex/skills/ - Parent directory
$REPO_ROOT/.codex/skills/ - Repository root
~/.codex/skills/ - User-level
/etc/codex/skills/ - System/admin level
Built-in skills - Bundled with Codex

Basic config.toml

# Model settings
model = "gpt-5.2-codex"
model_verbosity = "medium"  # high | medium | low
model_reasoning_effort = "high"  # low | high | xhigh

# Permissions
approval_policy = "on-failure"  # untrusted | on-failure | on-request | never
sandbox_mode = "workspace-write"  # read-only | workspace-write | danger-full-access
exec_timeout_ms = 300000  # 5 minutes

# Misc
file_opener = "cursor"  # Editor for opening files

Profiles

Define named profiles for different workflows:

[profiles.max]
model = "gpt-5.1-codex-max"
model_verbosity = "high"
model_reasoning_effort = "xhigh"

[profiles.fast]
model = "gpt-5.1-codex-mini"
model_verbosity = "low"
model_reasoning_effort = "low"

Usage:

codex -p max "complex refactoring task"
codex -p fast "quick fix"

MCP Servers

[mcp_servers.server-name]
command = "npx"
args = ["-y", "@package/mcp-server"]
enabled = true
tool_timeout_sec = 60.0

[mcp_servers.server-name.env]
API_KEY = "your-key"

Skills

Invoking Skills

# Explicit invocation
codex "$plan implement authentication"
codex "$skill-creator new skill for testing"

# Implicit (Codex decides based on context)
codex "plan out the implementation"

Built-in Skills

$plan - Research and create implementation plans
$skill-creator - Bootstrap new skills
$skill-installer - Download skills from GitHub

CLI Override

Override any config value at runtime:

codex -c model="o3"
codex -c 'sandbox_permissions=["disk-full-read-access"]'
codex -c shell_environment_policy.inherit=all

Convenience Flags

Flag	Equivalent
`--full-auto`	`-a on-request --sandbox workspace-write`
`--oss`	`-c model_provider=oss` (local LM Studio/Ollama)
`--search`	Enable web search tool

codex --full-auto "implement feature"
codex -C /path/to/project "work in different dir"
codex --add-dir /additional/path "access multiple dirs"

Quick Validation

# Check TOML syntax
cat ~/.codex/config.toml | toml-lint

# Test config override
codex -c model="test" --help

# Verify MCP servers
codex mcp list

Quick Troubleshooting

Config not loading: Verify ~/.codex/config.toml exists, check TOML syntax

MCP server not connecting: Check command path, verify API keys, check enabled = true

Skills not found: Verify path hierarchy, check SKILL.md exists in skill folder

Sandbox too restrictive: Use -s workspace-write, check project trust level

References

Detailed documentation for specific scenarios:

MCP Servers - Server configuration examples (Context7, Firecrawl, Graphite, Linear)
Troubleshooting - Common issues, debug commands, validation
Security - Sandbox modes, approval policies, trust levels, best practices

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: codex-configdescription: This skill should be used when configuring Codex CLI, setting up profiles, or when "config.toml", "sandbox mode", "Codex config", or "approval policy" are mentioned. Use when this capability is needed.---# Codex Configuration ManagementManages configuration files for OpenAI Codex CLI, including model settings, sandbox policies, MCP servers, and profiles.## Configuration Location**Primary Config:** `~/.codex/config.toml`**Skills Paths (precedence, highest first):**1. `$CWD/.codex/skills/` - Current directory2. `$CWD/../.codex/skills/` - Parent directory3. `$REPO_ROOT/.codex/skills/` - Repository root4. `~/.codex/skills/` - User-level5. `/etc/codex/skills/` - System/admin level6. Built-in skills - Bundled with Codex## Basic config.toml```toml# Model settingsmodel = "gpt-5.2-codex"model_verbosity = "medium" # high | medium | lowmodel_reasoning_effort = "high" # low | high | xhigh# Permissionsapproval_policy = "on-failure" # untrusted | on-failure | on-request | neversandbox_mode = "workspace-write" # read-only | workspace-write | danger-full-accessexec_timeout_ms = 300000 # 5 minutes# Miscfile_opener = "cursor" # Editor for opening files```## ProfilesDefine named profiles for different workflows:```toml[profiles.max]model = "gpt-5.1-codex-max"model_verbosity = "high"model_reasoning_effort = "xhigh"[profiles.fast]model = "gpt-5.1-codex-mini"model_verbosity = "low"model_reasoning_effort = "low"```**Usage:**```bashcodex -p max "complex refactoring task"codex -p fast "quick fix"```## MCP Servers```toml[mcp_servers.server-name]command = "npx"args = ["-y", "@package/mcp-server"]enabled = truetool_timeout_sec = 60.0[mcp_servers.server-name.env]API_KEY = "your-key"```## Skills### Invoking Skills```bash# Explicit invocationcodex "$plan implement authentication"codex "$skill-creator new skill for testing"# Implicit (Codex decides based on context)codex "plan out the implementation"```### Built-in Skills- `$plan` - Research and create implementation plans- `$skill-creator` - Bootstrap new skills- `$skill-installer` - Download skills from GitHub## CLI OverrideOverride any config value at runtime:```bashcodex -c model="o3"codex -c 'sandbox_permissions=["disk-full-read-access"]'codex -c shell_environment_policy.inherit=all```## Convenience Flags| Flag | Equivalent ||------|------------|| `--full-auto` | `-a on-request --sandbox workspace-write` || `--oss` | `-c model_provider=oss` (local LM Studio/Ollama) || `--search` | Enable web search tool |```bashcodex --full-auto "implement feature"codex -C /path/to/project "work in different dir"codex --add-dir /additional/path "access multiple dirs"```## Quick Validation```bash# Check TOML syntaxcat ~/.codex/config.toml | toml-lint# Test config overridecodex -c model="test" --help# Verify MCP serverscodex mcp list```## Quick Troubleshooting**Config not loading:** Verify `~/.codex/config.toml` exists, check TOML syntax**MCP server not connecting:** Check command path, verify API keys, check `enabled = true`**Skills not found:** Verify path hierarchy, check SKILL.md exists in skill folder**Sandbox too restrictive:** Use `-s workspace-write`, check project trust level## ReferencesDetailed documentation for specific scenarios:- **[MCP Servers](references/mcp-servers.md)** - Server configuration examples (Context7, Firecrawl, Graphite, Linear)- **[Troubleshooting](references/troubleshooting.md)** - Common issues, debug commands, validation- **[Security](references/security.md)** - Sandbox modes, approval policies, trust levels, best practices---> Converted and distributed by [TomeVault](https://tomevault.io/claim/outfitter-dev) — claim your Tome and manage your conversions.

Frequently asked questions

Codex Config