ralph
Self-referential loop until task completion with configurable verification reviewer
Install
With your agent
Install OMGSkills skill "yeachan-heo/oh-my-claudecode:ralph" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/Yeachan-Heo/oh-my-claudecode /tmp/oh-my-claudecode && ln -s /tmp/oh-my-claudecode/skills/ralph ~/.claude/skills/ralphFrom README
Parallel session caveats Multi-repo workspace anchor: drop a .omc-workspace marker at the parent directory so multiple sessions across sub-repos share one .omc/. Resolution order: OMCSTATEDIR > .omc-workspace > git > cwd. See docs/REFERENCE.md. Session id source: OMCSESSIONID env var wins in CLI contexts; hook payload data.sessionid wins in hook contexts. Plan id (when applicable): Two ralph runs in the same workspace will conflict on prd.json. Use distinct session IDs (the hook payload sessionid is already isolated per Claude Code session). For parallel ultragoal-backed ralph runs, use --plan-id.
More from this repo
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
ask
Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, Cursor, or Muse via `omc ask`, with...