Official Ralph Wiggum plugin (Anthropic)

Anthropic's first-party take on the Ralph loop: a Claude Code plugin that runs the iterate-fresh-context pattern with a managed stop and iteration mechanism built in.

prompt
→ Claude
Install the `ralph-wiggum` plugin from the anthropics/claude-code repo; it wraps the Ralph loop with a managed stop/iteration mechanism inside Claude Code.
claude-code

Implementation note

When to use: you want Ralph-style fresh-context iteration but would rather not hand-roll a bash while-loop and its stop logic — this is Anthropic's first-party packaging of the pattern. How it works: install the ralph-wiggum plugin from the anthropics/claude-code repo; it wraps the iterate-with-fresh-context loop inside Claude Code with a managed stop and iteration mechanism built in, so starting, bounding, and ending the loop are handled by the plugin rather than by shell plumbing you maintain yourself. Safety: the managed stop mechanism is the main advantage over the raw bash original, which loops forever by construction — here the halt logic is part of the tool. The usual Ralph rails still apply on top: run it against a repo where commits are cheap to revert, keep the per-iteration task small, and review the accumulated commits rather than trusting a long unattended run blindly.

Source: anthropics/claude-code

More automation loops

Run workflows with dynamic sub-agents

/goalnew

Split a task into packets, run sub-agents in parallel, synthesize results, and verify completion.

prompt
→ Claude
/goal loop and verify until complete
automationlow risk

Run agent turns until goal met

/goalnew

Agent executes repeated turns toward a condition, with a lightweight evaluator checking progress after each turn until the goal is reached.

prompt
→ Claude
/goal <condition turns a prompt into a durable objective. Thanos immediately starts a turn toward the condition, and after each turn a fresh, tool-less side-channel evaluator (a one-shot completeSimple call, not a subagent — so no extra agent turn and no re-entrancy) reads the last turn's evidence and returns MET / NOT MET . NOT MET auto-continues another turn with the reason as guidance; MET clears the goal and records the achievement. Unparseable evaluator output is treated as NOT MET (fail-safe: it never declares a false "done
automationmedium risk

Run agent until goal met

/goalnew

Queue agent turns with goal context until your objective is achieved, treating the goal as untrusted data.

prompt
→ Claude
/goal <objective , after /goal resume , and after every agent turn that leaves the goal active , the extension queues Codex's goal continuation prompt as hidden model-visible context. The objective is XML-escaped and wrapped as untrusted user data so it does not become higher-priority instructions
automationlow risk