javi22020/ralph
Skill Claude CodeCodex
Run an autonomous iterate-test-replan loop until a multi-step coding task is complete. Use this whenever the user asks Claude Code to work autonomously through a backlog, fix plan, or specification with minimal supervision — phrases like "ralph this", "loop until done", "keep iterating until tests pass", "work…
javi22020/ralph
Agent
Triage a stuck Ralph loop and propose either a revised fix plan, a specific question to ask the user, or a recommendation that the task is infeasible. Invoke when the Ralph circuit breaker has opened — repeated identical errors, no progress for several iterations, max iterations approaching, or a destructive action is…
javi22020/ralph
Agent
Critique a recent diff or implementation choice during the Ralph loop with a fresh, untainted context. Invoke when the parent agent has just made a non-trivial change (architectural decision, complex refactor, change touching unfamiliar code, change to security-sensitive paths) and wants a second opinion before…
javi22020/ralph
Agent
Run verification (tests, build, lint, type-check) for the Ralph loop and return a structured pass/fail summary without flooding the parent context. Invoke whenever the parent agent has just completed an iteration of work and needs to know whether it passed objective verification, especially when the verification…