debug

A debugging workflow for investigating bugs, failed tests, and unexpected behaviour through evidence and hypotheses.

In plain words
What is it for?
It is for understanding the issue, reproducing it, investigating the code, fixing the cause, and verifying the result.
Why use it?
It helps identify the underlying cause before changing code, reducing guesswork and repeated failed fixes.

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/ratler/dream-team/debug
Any agent
npx skills add Ratler/dream-team --skill debug
Clone the repo
git clone --depth 1 https://github.com/Ratler/dream-team

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 952 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 $0.00046 $0.00952
Opus 5 $0.00023 $0.00476
Sonnet 5 $0.00009 $0.00190
Haiku 4.5 $0.00005 $0.00095

Measured 2d ago against content hash d42fbea969d6, 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging Through Investigation

Help the user debug an issue through systematic investigation and hypothesis-driven problem solving. This is a conversation, not a fix-it script.

Start by understanding the issue, then reproduce it, form theories, investigate with evidence, and only fix once you understand the root cause.

The Process

Understanding the issue:

  • Explore the codebase first — read relevant files to build context before asking questions
  • Ask questions one at a time to understand the problem
  • Prefer multiple choice questions when possible, but open-ended is fine too
  • Only one question per message
  • Focus on understanding: expected behavior, actual behavior, reproduction steps, when it started, what changed recently

Reproducing the issue:

  • Attempt to reproduce the issue before investigating code
  • If this is a frontend/browser issue and you see playwright_* tools available, use them:
    • playwright_navigate to load the page
    • playwright_screenshot to capture visual evidence
    • playwright_click / playwright_fill to interact with elements
    • playwright_evaluate to check console errors and state
  • If this is a backend/CLI issue, run the reproduction steps with Bash
  • If this is a test failure, run the specific failing test
  • If you cannot reproduce, investigate why — environment, timing, specific data, concurrency
  • Document the reproduction case clearly — you need it later to verify the fix

Forming hypotheses:

  • Based on symptoms and code context, propose 2-3 theories about the root cause
  • For each theory: description, likelihood (high/medium/low), how to test it
  • Present theories to the user — they may have context that rules some out
  • Wait for user input before proceeding

Investigating:

  • Work through hypotheses starting with the most likely
  • Read relevant code paths — use Glob and Grep to find files, Read to inspect
  • Check logs, trace execution, inspect state
  • Use Playwright for frontend state inspection if available
  • Present findings as you go — if Theory A doesn't pan out, explain why and move to Theory B
  • Once you identify the root cause with evidence, present it clearly and wait for confirmation:

Read the full file on GitHub · 107 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 · 107 lines · 46 tokens per session scan A d42fbea969d6

Subscribe to this mod's changes

debug is a skill published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 952 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