debug

A guided debugging skill follows four stages: reproduce the problem, narrow it down, find its root cause, and fix it.

In plain words
What is it for?
Investigating software problems using the reported behavior, files, error messages, stack traces, or test names.
Why use it?
It gives debugging a clear order when the issue is an error, failed build, failed test, slow code, or incorrect behavior.

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/sh3rd3n/megazord/debug
Any agent
npx skills add Sh3rd3n/megazord --skill debug
Clone the repo
git clone --depth 1 https://github.com/Sh3rd3n/megazord

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,034 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 $0.00019 $0.03034
Opus 5 $0.00010 $0.01517
Sonnet 5 $0.00004 $0.00607
Haiku 4.5 $0.00002 $0.00303

Measured 2d ago against content hash 2323f56a14a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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.

skills/debug/SKILL.md · 328 lines

How it starts

The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mz:debug

Guide systematic four-phase debugging with observable state transitions. Each phase has a distinct banner so the user always knows which stage the debugging process is in. Adapts techniques based on issue type (runtime error, build failure, test failure, performance, logic bug).

Reference @skills/init/design-system.md for visual output formatting. Reference @skills/shared/terminology.md for official term definitions.

Step 1: Display Banner

Output the stage banner:

+===============================================+
|  MEGAZORD > DEBUG                             |
+===============================================+

Step 2: Gather Issue Context

Parse the user's description from the text after /mz:debug. If the description is insufficient (vague, missing key details), ask targeted clarifying questions:

  • What is the expected behavior?
  • What is the actual behavior?
  • When did it start happening?
  • Any recent changes?

If a file path, error message, stack trace, or test name is provided, use it as the starting point.

Issue Type Detection:

Categorize the issue to adapt techniques within each phase:

Type Signals Adapted Approach
Runtime error Stack trace, exception, crash, unhandled rejection Trace from stack, check inputs at each frame
Build failure Compile error, bundler error, type error at build time Check imports, types, config, dependency versions
Test failure Test name, assertion error, expected vs received Run specific test in isolation, check assertion values
Performance Slow, timeout, memory leak, high CPU Profile, measure baselines, compare before/after
Logic bug Wrong output, incorrect behavior, data corruption Add logging, trace data flow, check conditionals

Display the detected type:

> Issue type: {type}

Debug Mode Configuration

Read quality.debug from .planning/megazord.config.json (if config exists). If config does not exist, default to "systematic".

Read the full file on GitHub · 328 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. 2d ago First seen · 328 lines · 19 tokens per session scan A 2323f56a14a4

Subscribe to this mod's changes

debug is a skill published in the GitHub repository Sh3rd3n/megazord (3 stars, last pushed 6mo ago), licensed MIT. It adds 19 tokens to every session and 3,034 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 2026-08-31.

Related

Other skills, from other repositories

scrape

Scrape a URL to clean Markdown — use when asked to scrape, fetch, extract content from, or read a webpage and convert it to Markdown. Uses Jina Reader, Playwright, Camoufox (TLS-spoofing Firefox), Scweet (X/Twitter), Firecrawl, or WebFetch.

5uck1ess/devkit · 66 tokens

browser

Automate a web browser — use when asked to click buttons, fill forms, navigate multi-step flows, extract data from JS-rendered pages, log into a site, record user interactions, or test a web app in a real browser. Use for anything beyond simple article scraping.

5uck1ess/devkit · 58 tokens

creating-workflows

REFERENCE ONLY — schema documentation for authoring devkit workflow YAML files (step types, variable interpolation, loops, parallel groups, examples). NOT a runnable workflow. Load this only when asked to write or modify a workflow YAML, never on natural-language task requests.

5uck1ess/devkit · 56 tokens

health

Check devkit health — which external CLIs (codex, gemini, gh, rtk, sg, gcli) are installed, which agents are available, which skills are ready to use. Use when asked about devkit health, devkit status, "is devkit working?", "what's installed?", "what devkit capabilities do I have?", diagnosing devkit setup issues, or…

5uck1ess/devkit · 99 tokens

screenshot

Capture a screenshot or PDF of a web page — use when asked to screenshot a URL, capture a page, take a picture of a website, generate a visual snapshot, or save a page as PDF. Supports full page, element selector, device emulation, and custom viewport.

5uck1ess/devkit · 59 tokens

gcli

Google Workspace CLI (Gmail, Calendar, Drive) via gcli — use --for-ai flag for token-efficient structured output.

5uck1ess/devkit · 29 tokens