Skill Claude CodeCodex
Reduce AI-generated slop with a regression-tests-first, smell-by-smell cleanup workflow that preserves behavior and raises signal quality.
24 8d ago A 21 tokens
original MIT
24Stars on the repository
60Mods indexed here, across every type
8d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
analyze
02Skill Claude CodeCodex
Use this skill to answer the user’s question through read-only repository analysis. The goal is to explain what the codebase most likely says about the question, not to drift into implementation, debugging theater, or generic fix planning.
24 8d ago A 69 tokens
original MIT
ask-claude
03Skill Claude CodeCodex
Use the locally installed Claude CLI as a direct external advisor for focused questions, reviews, or second opinions.
24 8d ago A 19 tokens
original MIT
ask-gemini
04Skill Claude CodeCodex
Use the locally installed Gemini CLI as a direct external advisor for brainstorming, design feedback, and second opinions.
24 8d ago A 19 tokens
original MIT
autopilot
05Skill Claude CodeCodex
Autopilot is the strict autonomous delivery loop for non-trivial work. Its primary contract is exactly.
24 8d ago A 23 tokens
original MIT
autoresearch
06Skill Claude CodeCodex
Autoresearch is the skill-first replacement for the deprecated omx autoresearch command. It keeps the useful measured-research loop, but it now runs as a native-hook stateful workflow instead of a direct CLI or tmux launch surface.
24 8d ago A 17 tokens
original MIT
cancel
07Skill Claude CodeCodex
Intelligent cancellation that detects and cancels the active OMX mode.
24 8d ago C 39 tokens
original MIT
code-review
08Skill Claude CodeCodex
Conduct a thorough code review for quality, security, and maintainability with severity-rated feedback.
24 8d ago A 12 tokens
original MIT
Skill Claude CodeCodex
Unified and only entry point for notification setup.
24 8d ago A 18 tokens
original MIT
Skill Claude CodeCodex
Deep Interview is an intent-first Socratic clarification loop before planning or implementation. It turns vague ideas into execution-ready specifications by asking targeted questions about why the user wants a change, how far it should go, what should stay out of scope, and what OMX may decide without confirmation.
24 8d ago A 19 tokens
original MIT
doctor
11Skill Claude CodeCodex
Note: All /.codex/... paths in this guide respect CODEXHOME when that environment variable is set.
24 8d ago D 16 tokens
original MIT
help
12Skill Claude CodeCodex
Plain English works as best-effort guidance — OMX inspects each prompt and may add advisory routing context to steer the model toward a suitable lane. This is advisory prompt-routing context: it does not activate a skill or workflow by itself. Explicit keywords remain the deterministic control surface when you want…
24 8d ago A 15 tokens
original MIT
hud
13Skill Claude CodeCodex
The OMX HUD uses a two-layer architecture.
24 8d ago B 18 tokens
original MIT
note
14Skill Claude CodeCodex
Save important context to .omx/notepad.md that survives conversation compaction.
24 8d ago A 16 tokens
original MIT
omx-setup
15Skill Claude CodeCodex
Use this skill when users want to install or refresh oh-my-codex for the current project plus user-level OMX directories.
24 8d ago B 21 tokens
original MIT
pipeline
16Skill Claude CodeCodex
$pipeline is the configurable pipeline orchestrator for OMX. It sequences stages through a uniform PipelineStage interface, with state persistence and resume support.
24 8d ago A 14 tokens
original MIT
plan
17Skill Claude CodeCodex
Plan creates comprehensive, actionable work plans through intelligent interaction. It auto-detects whether to interview the user (broad requests) or plan directly (detailed requests), and supports consensus mode (iterative Planner/Architect/Critic loop with RALPLAN-DR structured deliberation) and review mode (Critic…
24 8d ago A 12 tokens
original MIT
ralph
18Skill Claude CodeCodex
Skill "ralph" from Orinks/AccessiWeather, covering state management, scenario examples, prd mode (optional), detecting prd mode and detecting --no-deslop.
24 8d ago A 18 tokens
original MIT
ralplan
19Skill Claude CodeCodex
Ralplan is a shorthand alias for $plan --consensus. It triggers iterative planning with Planner, Architect, and Critic agents until consensus is reached, with RALPLAN-DR structured deliberation (short mode by default, deliberate mode for high-risk work).
24 8d ago A 14 tokens
original MIT
Skill Claude CodeCodex
Conduct a thorough security audit checking for OWASP Top 10 vulnerabilities, hardcoded secrets, and unsafe patterns.
24 8d ago A 14 tokens
original MIT
skill
21Skill Claude CodeCodex
Meta-skill for managing oh-my-codex skills via CLI-like commands.
24 8d ago B 22 tokens
original MIT
team
22Skill Claude CodeCodex
$team is the tmux-based parallel execution mode for OMX. It starts real worker Codex and/or Claude CLI sessions in split panes and coordinates them through .omx/state/team/... files plus CLI team interop (omx team api ...) and state files.
24 8d ago C 19 tokens
original MIT
trace
23Skill Claude CodeCodex
Skill "trace" from Orinks/AccessiWeather, covering agent flow trace, objective, instructions and output format.
24 8d ago A 13 tokens
original MIT
ultraqa
24Skill Claude CodeCodex
Skill "ultraqa" from Orinks/AccessiWeather, covering ultraqa skill, gpt-5.5 guidance alignment, goal parsing, cycle workflow and cycle n (max 5).
24 8d ago A 22 tokens
original MIT