oh-my-codex

Multi-agent orchestration layer for OpenAI Codex CLI. Provides 30 specialized agents, 40+ workflow skills, team orchestration in tmux, persistent MCP servers, and staged pipeline execution.

1.38x

Quality

48%

Does it follow best practices?

Impact

100%

1.38x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent-skills/oh-my-codex/SKILL.md

Evaluation results

100%

Developer Onboarding: Multi-Agent Orchestration Setup

OMX installation and project configuration

Criteria

Without context

With context

Correct package name

100%

Global npm install

100%

omx setup step

100%

omx doctor diagnostics

100%

xhigh reasoning flag

100%

madmax flag

100%

madmax flag meaning

100%

AGENTS.md injection

100%

AGENTS.md bypass env var

100%

Custom instructions env var

100%

Role prompt syntax

100%

Workflow skill syntax

100%

Output files produced

100%

82%

Parallel Refactor: Multi-Agent Team Orchestration

Team mode orchestration and staged pipeline

Criteria

Without context

With context

omx doctor --team pre-check

100%

Correct team start syntax

100%

Team status command

100%

Team shutdown command

100%

Team resume command

100%

Pipeline stage order

100%

Workflow skill trigger syntax

100%

Role prompt syntax

100%

omx_state persistence mention

100%

xhigh and madmax flags

100%

Output script produced

100%

Executor or other valid role

25%

100%

Session Activity Tracker: Integrating Lifecycle Hooks

Hook plugin lifecycle integration

Criteria

Without context

With context

OMX_HOOK_PLUGINS env var

100%

Plugin file location

100%

Plugin file extension .mjs

100%

omx hooks init command

100%

omx hooks validate command

100%

omx hooks test command

100%

session-start event

100%

session-end event

100%

turn-complete event

100%

omx hooks status command

100%

Actual .mjs plugin file created

100%

Repository: supercent-io/skills-template
Commit: fd18296

Evaluated: 28 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Developer Onboarding: Multi-Agent Orchestration Setup Parallel Refactor: Multi-Agent Team Orchestration Session Activity Tracker: Integrating Lifecycle Hooks

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.