Agent skill
omx-setup
Setup and configure oh-my-codex using current CLI behavior
Install this agent skill to your Project
npx add-skill https://github.com/Yeachan-Heo/oh-my-codex/tree/main/skills/omx-setup
SKILL.md
OMX Setup
Use this skill when users want to install or refresh oh-my-codex for the current project plus user-level OMX directories.
Command
omx setup [--force] [--dry-run] [--verbose] [--scope <user|project>]
If you only want lightweight AGENTS.md scaffolding for an existing repo or subtree, use omx agents-init [path] instead of full setup.
Supported setup flags (current implementation):
--force: overwrite/reinstall managed artifacts where applicable--dry-run: print actions without mutating files--verbose: print per-file/per-step details--scope: choose install scope (user,project)
What this setup actually does
omx setup performs these steps:
- Resolve setup scope:
--scopeexplicit value- else persisted
./.omx/setup-scope.json(with automatic migration of legacy values) - else interactive prompt on TTY (default
user) - else default
user(safe for CI/tests)
- Create directories and persist effective scope
- Install prompts, native agent configs, skills, and merge config.toml (scope determines target directories)
- Verify Team CLI API interop markers exist in built
dist/cli/team.js - Generate project-root
./AGENTS.mdfromtemplates/AGENTS.md(or skip when existing and no force) - Configure notify hook references and write
./.omx/hud-config.json
Important behavior notes
omx setuponly prompts for scope when no scope is provided/persisted and stdin/stdout are TTY.- Local project orchestration file is
./AGENTS.md(project root). - If
AGENTS.mdexists and--forceis not used, interactive TTY runs ask whether to overwrite. Non-interactive runs preserve the file. - Scope targets:
user: user directories (~/.codex,~/.codex/skills,~/.omx/agents)project: local directories (./.codex,./.codex/skills,./.omx/agents)
- Migration hint: in
userscope, if historical~/.agents/skillsstill exists alongside${CODEX_HOME:-~/.codex}/skills, current setup prints a cleanup hint because Codex may show duplicate skill entries until the legacy tree is removed or archived. - If persisted scope is
project,omxlaunch automatically usesCODEX_HOME=./.codexunless user explicitly overridesCODEX_HOME. - With
--force, AGENTS overwrite may still be skipped if an active OMX session is detected (safety guard). - Legacy persisted scope values (
project-local) are automatically migrated toprojectwith a one-time warning.
Recommended workflow
- Run setup:
omx setup --force --verbose
- Verify installation:
omx doctor
- Start Codex with OMX in the target project directory.
Expected verification indicators
From omx doctor, expect:
- Prompts installed (scope-dependent: user or project)
- Skills installed (scope-dependent: user or project)
- AGENTS.md found in project root
.omx/stateexists- OMX MCP servers configured in scope target
config.toml(~/.codex/config.tomlor./.codex/config.toml)
Troubleshooting
- If using local source changes, run build first:
npm run build
- If your global
omxpoints to another install, run local entrypoint:
node bin/omx.js setup --force --verbose
node bin/omx.js doctor
- If AGENTS.md was not overwritten during
--force, stop active OMX session and rerun setup.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
configure-notifications
Configure OMX notifications - unified entry point for all platforms
ultraqa
QA cycling workflow - test, verify, fix, repeat until goal met
build-fix
Fix build and TypeScript errors with minimal changes
ask-claude
Ask Claude via local CLI and capture a reusable artifact
tdd
Test-Driven Development enforcement skill - write tests first, always
analyze
Run deep investigation of architecture, bugs, performance issues, or dependencies and return structured findings with file:line evidence. Use when a user says 'analyze', 'investigate', 'why does', 'what's causing', or needs root cause analysis before making changes. Routes to architect agent or Codex MCP for thorough cross-file reasoning.
Didn't find tool you were looking for?