npx claudepluginhub baleen37/bstack --plugin ralphThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Stop hook keeps you running until you write the cancel signal.
mkdir -p .ralph/state/.ralph/state/ralph-activating with the task description--no-prd to skip → auto-generate single-story prd)Create .ralph/prd.json: project, userStories[] each with id, title, acceptanceCriteria[], priority, passes:false. Small testable stories, dependency-ordered.
.ralph/progress.txt if it existspasses:false storypasses:true. Fail → append [ITER N] US-XXX: <reason> to .ralph/progress.txt--critic=none to skip)--no-deslop to skip).ralph/state/cancel-signal-state.json ({})<promise>COMPLETE</promise>