clawhip × OMX (oh-my-codex)
Launch [OMX](https://github.com/Yeachan-Heo/oh-my-codex) coding sessions with clawhip monitoring.
Best use case
clawhip × OMX (oh-my-codex) is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Launch [OMX](https://github.com/Yeachan-Heo/oh-my-codex) coding sessions with clawhip monitoring.
Teams using clawhip × OMX (oh-my-codex) should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/omx/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How clawhip × OMX (oh-my-codex) Compares
| Feature / Agent | clawhip × OMX (oh-my-codex) | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Launch [OMX](https://github.com/Yeachan-Heo/oh-my-codex) coding sessions with clawhip monitoring.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# clawhip × OMX (oh-my-codex) Launch [OMX](https://github.com/Yeachan-Heo/oh-my-codex) coding sessions with clawhip monitoring. ## Source of truth clawhip owns the OMC/OMX integration doctrine. Use these docs for setup, routing policy, and troubleshooting: - quick operator flow: [`README.md`](../../README.md) - detailed OMX runbook: [`integrations/omx/README.md`](../../integrations/omx/README.md) - native routing/reference contract: [`docs/native-event-contract.md`](../../docs/native-event-contract.md) This skill should stay focused on OMX session-launch mechanics and local defaults. ## Prerequisites - [clawhip](https://github.com/Yeachan-Heo/clawhip) installed and daemon running - [OMX](https://github.com/Yeachan-Heo/oh-my-codex) installed - tmux ## Usage ### Create a session ```bash ./create.sh <session-name> <worktree-path> [prompt] [channel-id] [mention] ``` ```bash # Basic — uses clawhip default channel ./create.sh issue-123 ~/my-project/worktrees/issue-123 # Start a session and auto-send an initial prompt after the TUI initializes ./create.sh issue-123 ~/my-project/worktrees/issue-123 "Fix the bug in src/main.rs and create a PR to dev" # With prompt, specific channel, and mention ./create.sh issue-123 ~/my-project/worktrees/issue-123 "Fix the bug in src/main.rs and create a PR to dev" 1234567890 "<@user-id>" ``` `create.sh` emits native clawhip v1 hook envelopes directly from the OMX shell session via `clawhip omx hook`. If you pass a prompt, the script waits 10 seconds for the TUI to initialize, then sends the prompt via `tmux send-keys -l` before pressing Enter. ### Send a prompt ```bash ./prompt.sh <session-name> "Fix the bug in src/main.rs and create a PR to dev" ``` `prompt.sh` sends prompt text in tmux literal mode (`send-keys -l`) and presses Enter separately so quotes, punctuation, and leading dashes are preserved exactly. ### Monitor output ```bash ./tail.sh <session-name> [lines] ``` ## Customization ### Environment variables | Variable | Default | Description | |----------|---------|-------------| | `CLAWHIP_OMX_KEYWORDS` | `error,Error,FAILED,PR created,panic,complete` | Comma-separated keywords to monitor | | `CLAWHIP_OMX_STALE_MIN` | `30` | Minutes before stale alert | | `CLAWHIP_OMX_FLAGS` | `--madmax` | Extra flags passed to `omx` | | `CLAWHIP_OMX_ENV` | *(empty)* | Extra env vars prepended to omx command (e.g. `FOO=1 BAR=2`) | | `CLAWHIP_OMX_PROJECT` | detected from the git common dir (fallback: worktree name) | Override the project name sent in lifecycle events | ### Config defaults Set defaults in `~/.clawhip/config.toml`: ```toml [skills.omx] channel = "1234567890" mention = "<@your-user-id>" keywords = "error,Error,FAILED,PR created,complete" stale_minutes = 30 flags = "--madmax" ```
Related Skills
clawhip × OMC (oh-my-claudecode)
Launch [OMC](https://github.com/Yeachan-Heo/oh-my-claudecode) coding sessions with clawhip monitoring.
clawhip × filesystem-offloaded memory
Use this skill when you want a Claw OS-style memory system where `MEMORY.md` stays small and points into a structured `memory/` tree.
clawhip
Attach/install/use clawhip as a daemon-first notification gateway runtime for OpenClaw / Clawdbot
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI. Use when you want professional code review before commits, you need automatic CHANGELOG generation, or reviewing large-scale refactoring.
codex
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".
codex
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI
codex-cli-guardian
Codex CLI 会话守护者。管理 API Key、任务执行与结果摘要。提供后台模式运行、API Key 验证、会话锁定与PID追踪等功能。
cpa-codex-auth-sweep-cliproxy
通过 CLI Proxy Management API 拉取 Codex 认证文件并高并发探活扫描。适用于「扫号」「清死号」「清理 Codex 401」场景;仅在用户明确确认后可删除 401。执行前必须提供 base_url 与 management_key。安全限制:默认仅允许 https://chatgpt.com 作为 probe 主机,非白名单目标需显式危险确认。
secretcodex
Generate creative code names and encode/decode secret messages using classic and sophisticated ciphers. Blends nostalgic decoder ring fun with modern cryptographic techniques. Includes Caesar, Vigenère, Polybius, Rail Fence, and hybrid methods. Provides keys for secure message sharing between trusted parties.
codex-cli
Use OpenAI Codex CLI for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding agent, gpt-5-codex. Enables Clawdbot to delegate coding work to Codex CLI as a subagent or direct tool.
codex-bridge
Dispatch coding tasks to the local OpenAI Codex CLI with background execution, status polling, and answerable clarifying questions. Use when OpenClaw should delegate script building, code edits, refactors, or multi-step coding work to Codex from the command line.