Skip to content

tim-hub/powerball-harness / harness/skills/harness-ralph-loop

harness-ralph-loop

Verified

Runs iterate-until-pass loops with ralph-worker agents in a worktree. Use when running [ralph]-marked tasks or looping until verify passes.

Harness Ralph Loop

Iterative-loop orchestrator for [ralph]-marked Plans.md tasks. Spawns a fresh harness:ralph-worker subagent per attempt inside a single persistent worktree, runs the Verify command authoritatively, and loops until both the <promise> text tag and verify exit 0 agree.

Quick Reference

Subcommand / ArgumentBehavior
helpPrint usage, philosophy, and link to prompt-best-practices.md
<task-id>Run the loop for a Plans.md task that has [ralph] marker
--max-iter NOverride MaxIter (default: 10)
--verify CMDOverride the Verify command from the task

Execution Flow

See references/loop-flow.md for the complete orchestrator pseudocode.

Summary: On iteration 0 the orchestrator spawns a ralph-worker with isolation="worktree" to create the persistent worktree, capturing RALPH_WORKTREE from result.worktreePath. For iterations 1..N it fetches the EnterWorktree deferred-tool schema via ToolSearch, calls EnterWorktree(path=RALPH_WORKTREE), then spawns the next worker without the isolation param. After each iteration the orchestrator runs the Verify command itself (anti-tamper), compares the exit code against ralph-worker-report.v1.verify.exit_code, scans the final assistant message for <promise>…</promise>, and diffs the worktree to detect stuck iterations. The loop terminates on success or on any of the three hard-stop failure modes (FT-RALPH-01 STUCK, FT-RALPH-02 VERIFY-MISMATCH, FT-RALPH-03 MAX-ITER).

Help Subcommand

Running harness-ralph-loop help prints the following:

  1. Overview — harness-ralph-loop is an iterative-loop orchestrator that spawns a fresh ralph-worker subagent per attempt inside a single persistent worktree, runs the Verify command authoritatively, and loops until both the <promise> text tag and verify exit 0 agree.

  2. Philosophy bullets:

    • Iteration > Perfection — let the loop refine; don't aim for perfect on the first try
    • Failures Are Data — deterministically bad means tunable; each failure leaves context
    • Operator Skill Matters — prompt quality is the primary lever, not model strength
    • Persistence Wins — keep trying; the loop handles retry logic automatically
  3. Prompt guidance pointer: For full prompt-writing guidance see prompt-best-practices.md

  4. Task-pattern fit pointer: For task-pattern fit see when-to-ralph.md

When to Use Ralph

See references/when-to-ralph.md for guidance on which tasks are Ralph-suitable and which are not.

Reference Files

FilePurpose
references/loop-flow.mdFull orchestrator pseudocode, prompt template, decision matrix, terminal-state handling
references/when-to-ralph.mdWhen to use Ralph (task patterns, DoD quality checks)
references/prompt-best-practices.mdPrompt writing best practices (A1–A4), philosophy bullets, learn-more links

Related Skills and Agents

  • harness-plan — Emits [ralph] marker + Verify: line for suitable tasks
  • harness-work — Detects [ralph] marker and routes to this skill
  • harness:ralph-worker — The per-iteration worker agent this skill dispatches
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall