From ralphex
Launches ralphex CLI to execute Markdown plans autonomously, with installation verification, mode/plan/iteration prompts, and progress monitoring via Bash.
npx claudepluginhub umputun/ralphex --plugin ralphexThis skill is limited to using the following tools:
**SCOPE**: This command ONLY launches ralphex, monitors progress, and reports status. Do NOT take any other actions.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
SCOPE: This command ONLY launches ralphex, monitors progress, and reports status. Do NOT take any other actions.
Check if ralphex CLI is installed:
which ralphex
If not found, guide installation based on platform:
brew install umputun/apps/ralphex.deb from https://github.com/umputun/ralphex/releases.rpm from https://github.com/umputun/ralphex/releasesgo install github.com/umputun/ralphex/cmd/ralphex@latestUse AskUserQuestion to confirm installation method, then guide through it. Do not proceed until which ralphex succeeds.
Check $ARGUMENTS for optional plan file path:
Use AskUserQuestion:
If Full mode selected:
docs/plans/*.md (excludes completed/)If Review or Codex-only mode selected:
docs/plans/**/*.md (includes completed/ for context)Use AskUserQuestion:
Build and run the command:
ralphex \
[--review] # if user selected "Review" mode
[--codex-only] # if user selected "Codex-only" mode
[--max-iterations N] # from user selection (25, 50, or 100)
[plan-file] # from argument OR plan selection (omit if "None" selected)
Run using Bash tool with run_in_background: true. Save the task_id from the response - needed for status checks later.
Determine progress filename based on mode and plan selection:
.ralphex/progress/progress-{plan-stem}.txt.ralphex/progress/progress-{plan-stem}-review.txt.ralphex/progress/progress-{plan-stem}-codex.txt.ralphex/progress/progress.txt.ralphex/progress/progress-review.txt.ralphex/progress/progress-codex.txtWhere {plan-stem} is the plan filename without extension (e.g., fix-bugs from fix-bugs.md).
tail -20 [progress-filename]ralphex started. Task ID: [task_id]
Plan: [plan file from progress file]
Branch: [branch from progress file]
Mode: [mode from progress file]
Progress file: [progress-filename]
Manual monitoring:
tail -f [progress-filename] # live stream
tail -50 [progress-filename] # recent activity
ralphex runs autonomously (can take hours). Process continues if you close this conversation.
Ask "check ralphex" to get status update.
STOP HERE after reporting launch status. Do not continue monitoring automatically.
If user explicitly asks "check ralphex", "ralphex status", or "how is ralphex doing":
block: false to check process status (use task_id from Step 5)If process still running:
If process exited (TaskOutput shows completion):
After reporting status, STOP. Do not offer to do anything else.
ralphex automatically strips the CLAUDECODE env var from child processes, allowing it to run from inside Claude Code. If the nested session error is somehow encountered, ralphex detects it via error pattern matching and exits gracefully instead of looping.
Running from a standalone terminal is still recommended for the best experience.