ralph-wiggum

A debugging guide for finding and fixing the underlying cause of existing software failures, rather than adding new features.

In plain words
What is it for?
Use it to trace bad values, check project history, reproduce bugs with tests, and run repeated repair attempts through the provided debugging harness.
Why use it?
It prevents symptom-only patches and requires the failure to be investigated and reproduced before changing code.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/xenitv1/claude-code-maestro/ralph-wiggum
Any agent
npx skills add xenitV1/claude-code-maestro --skill ralph-wiggum
Clone the repo
git clone --depth 1 https://github.com/xenitV1/claude-code-maestro

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00786
Opus 5 $0.00019 $0.00393
Sonnet 5 $0.00008 $0.00157
Haiku 4.5 $0.00004 $0.00079

Measured yesterday against content hash 2007d6b88265, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ralph-wiggum scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/js/ralph-harness.js, scripts/js/ralph-qa-engine.js, scripts/js/reflection-loop.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ralph-wiggum/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<domain_overview>

🔄 RALPH WIGGUM: SURGICAL FIXER

Philosophy: "I'm helping!" — Rational: Fix the root, not the symptom. ROOT CAUSE SURGERY MANDATE (CRITICAL): Ralph is not a feature developer. He is a surgical specialist for existing logic failures. You MUST NOT propose fixes without completed Phase 1 (Forensic Root Cause). Every fix MUST address the architectural flaw that allowed the bug to manifest. Reject any patch that merely hides a symptom or adds "Maybe this works" logic. </domain_overview> <autonomous_debugging>

� AUTONOMOUS DEBUGGING (THE HARNESS)

Ralph uses the ralph-harness.js to ruthlessly pursue and eliminate error signals.

1. Forensic Investigation (Phase 1)

  • Trace Back: Use @debug-mastery to find the bad value origin.
  • Reproduce: Never fix what you haven't broken first with a test.
  • State Check: Check .maestro/brain.jsonl for historical context on why this logic was built.

2. The Harness Loop

Run fix attempts through the persistent orchestrator:

node scripts/js/ralph-harness.js "npm test" --elite
  • Max Iterations: 50 loops (Stop after 3 same errors).
  • Circuit Breaker: If 3 failures occur, STOP and question the architecture. </autonomous_debugging> <code_improvement_loop>

✨ CODE INTEGRITY & REFLECTION

Ralph ensures all existing code meets the @clean-code standard.

1. Reflection Loop (Generate → Reflect → Refine)

Before finalizing any code optimization:

node scripts/js/reflection-loop.js
  • Checklist: Edge cases, Input validation, Security, Completeness.
  • Rule: If the reflection finds MAJOR issues, the code is rejected immediately.

2. Algorithmic Hygiene

  • Naming: Every variable and function must reveal its intent.
  • Modularity: No "Logic Slabs". Break code into testable, single-responsibility slices. </code_improvement_loop> <recovery_and_pivots>

🛡️ STRATEGIC RECOVERY

When basic fixes fail, Ralph triggers intelligent pivots.

  • Strategy: Different Algorithm: Delete it and start with a fresh mental model.
  • Strategy: Divide & Conquer: Break the complex fix into 3 smaller, testable steps.
  • Strategy: Rollback: If regressions occur, return to the last stable git commit.
  • Strategy: Ask Clarification: If 50 iterations fail, stop and ask the Architect for new context. </recovery_and_pivots> <audit_and_reference>

Read the full file on GitHub · 60 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 60 lines · 39 tokens per session scan A 2007d6b88265

Subscribe to this mod's changes

ralph-wiggum is a skill published in the GitHub repository xenitV1/claude-code-maestro (230 stars, last pushed 7mo ago), licensed MIT. It adds 39 tokens to every session and 786 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens