skill-debug

skill-debug is a skill for Claude Code, Codex from nyldn/claude-octopus. It costs 20 tokens per session (2,978 once invoked), scanned A, original, MIT.

A four-phase method for investigating software bugs, test failures, build failures, performance problems, and other unexpected behavior.

In plain words
What is it for?
Use it to diagnose technical problems systematically, with no more than three attempted fixes before asking the user for direction.
Why use it?
It reduces guesswork by requiring root-cause investigation and a stated hypothesis before proposing fixes.

Skill for Claude CodeCodex

Part of the octo plugin — 47 skills, 10 agents, 2 hooks shipped together

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/nyldn/claude-octopus/skill-debug
Any agent
npx skills add nyldn/claude-octopus --skill skill-debug
Clone the repo
git clone --depth 1 https://github.com/nyldn/claude-octopus

Made for: Claude Code, Codex.

Or install octo, the plugin that ships this one along with the rest of its 47 skills, 10 agents, 2 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-debug.svg)](https://agentmods.dev/skills/nyldn/claude-octopus/skill-debug)
Your own site
<a href="https://agentmods.dev/skills/nyldn/claude-octopus/skill-debug"><img src="https://agentmods.dev/badge/skills/nyldn/claude-octopus/skill-debug.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,978 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 $0.00020 $0.02978
Opus 5 $0.00010 $0.01489
Sonnet 5 $0.00004 $0.00596
Haiku 4.5 $0.00002 $0.00298

Measured 4d ago against content hash b1861bed5ba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-debug 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 4d ago.

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.

.claude/skills/skill-debug/SKILL.md · 399 lines

How it starts

The opening of the file, as written. The whole thing — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging

MANDATORY COMPLIANCE — DO NOT SKIP

When this skill is invoked, you MUST follow the 4-phase debugging process below. You are PROHIBITED from:

  • Jumping straight to a fix without completing Phase 1 (Root Cause Investigation)
  • Skipping the hypothesis step and guessing at solutions
  • Deciding the bug is "obvious" and bypassing the systematic process
  • Attempting more than 3 fixes without stopping to ask the user

Systematic debugging finds root causes in 15-30 minutes. Random fixes waste 2-3 hours. Follow the process.


Your first output line MUST be: 🐙 **CLAUDE OCTOPUS ACTIVATED** - Systematic Debugging

The Iron Law

Random fixes waste time and create new bugs. Quick patches mask underlying issues.

If you haven't completed Phase 1, you cannot propose fixes.

When to Use

Use for ANY technical issue:

  • Test failures
  • Bugs in production
  • Unexpected behavior
  • Performance problems
  • Build failures
  • Integration issues

Use ESPECIALLY when:

  • Under time pressure (emergencies make guessing tempting)
  • "Just one quick fix" seems obvious
  • You've already tried multiple fixes
  • Previous fix didn't work

The Four Phases

┌──────────────────┐
│ Phase 1: ROOT    │ ← Understand WHAT and WHY
│ CAUSE            │
└────────┬─────────┘
         ↓
┌──────────────────┐
│ Phase 2: PATTERN │ ← Find working examples
│ ANALYSIS         │
└────────┬─────────┘
         ↓
┌──────────────────┐
│ Phase 3:         │ ← Form and test hypothesis
│ HYPOTHESIS       │
└────────┬─────────┘
         ↓
┌──────────────────┐
│ Phase 4:         │ ← Fix root cause, not symptom
│ IMPLEMENTATION   │
└──────────────────┘

You MUST complete each phase before proceeding.


Phase 1: Root Cause Investigation

BEFORE attempting ANY fix:

1. Read Error Messages Carefully

  • Don't skip past errors or warnings
  • Read stack traces completely
  • Note line numbers, file paths, error codes
  • Error messages often contain the exact solution

Read the full file on GitHub · 399 lines

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. 4d ago First seen · 399 lines · 20 tokens per session scan A b1861bed5ba2

Subscribe to this mod's changes

skill-debug is a skill published in the GitHub repository nyldn/claude-octopus (4,035 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 2,978 once invoked, about $0.0001 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

contextdocs

Your AI agent maintains its own context files — a Claude Code plugin with an AGENTS-first model that covers Codex, Copilot, Cursor, Gemini, and 3 more tools. Signal Gate filtering, Context Guard hooks, health scoring, and MEMORY.md promotion.

littlebearapps/contextdocs · 56 tokens

doctor

Diagnose whether Skill Autopilot's hooks are actually firing and config is valid. Use when the autopilot seems inactive, suggestions never appear, after install or update to verify setup, or the user says "autopilot不工作", "check autopilot", "autopilot broken".

WinterDDo/claude-code-skill-autopilot · 61 tokens

ai-context

Generates, updates, and audits AGENTS-first AI IDE context files. Builds canonical AGENTS.md plus thin bridges for Claude Code, Cursor (modern .cursor/rules/.mdc), Copilot, Cline (.clinerules/ directory), Windsurf, Gemini CLI, Codex CLI, and OpenCode. Use for creating, regenerating, fixing, or promoting context files…

littlebearapps/contextdocs · 86 tokens

legal-document-generator

Generate draft legal documents from company context. Supports 8 document types across US, EU/GDPR, and UK jurisdictions.

jikig-ai/soleur · 29 tokens

api-design-reviewer

Expert API design reviewer for REST, GraphQL, and gRPC APIs. Analyzes API designs for security, performance, consistency, scalability, and maintainability. Use when designing new APIs, reviewing API proposals, auditing existing endpoints, or before major API releases. Covers authentication, error handling, pagination…

shahtuyakov/claude-setup · 82 tokens

task-breakdown

Break down complex development requests into discrete, actionable tasks. Use when analyzing new features, integrations, refactoring requests, or any multi-component work that needs to be sequenced across agents. Provides patterns for identifying components, dependencies, and complexity.

shahtuyakov/claude-setup · 52 tokens