debugging

A structured method for finding and fixing software bugs. It starts by reproducing the problem, comparing expected and actual behavior, gathering evidence, and narrowing down the failing part.

In plain words
What is it for?
Use it to investigate runtime errors, broken features, failing tests, performance problems, and reports that something is not working.
Why use it?
It replaces guesswork with a repeatable investigation, making errors, test failures, slow behavior, and unfamiliar code easier to understand.

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/macromania/agentop/debugging
Any agent
npx skills add macromania/agentop --skill debugging
Clone the repo
git clone --depth 1 https://github.com/macromania/agentop

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,988 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 $0.00052 $0.01988
Opus 5 $0.00026 $0.00994
Sonnet 5 $0.00010 $0.00398
Haiku 4.5 $0.00005 $0.00199

Measured yesterday against content hash cd89aa8fb38f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugging 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.

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.

.github/skills/debugging/SKILL.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging

A structured approach to isolating and resolving bugs efficiently, based on proven debugging methodologies.

When to Use This Skill

  • Encountering runtime errors
  • Test failures
  • Unexpected behavior
  • Performance issues
  • Investigating reported bugs
  • Understanding unfamiliar code

Debugging Methodology

Phase 1: Understand the Problem

Before touching code, gather information:

  1. Reproduce the Issue

    • Get exact reproduction steps
    • Identify what triggers the bug
    • Note when it started (recent changes?)
  2. Define Expected vs Actual

    Expected: User clicks "Start Session" → Session starts, UI shows running state
    Actual: User clicks "Start Session" → Nothing happens, no error in console
    
  3. Gather Context

    • Check error messages and stack traces
    • Review recent git commits
    • Check if it worked before (and what changed)

Phase 2: Isolate the Problem

Narrow down the scope systematically:

// Binary search approach to find failing point
async function startSession(outcomeId: string) {
  console.log('[DEBUG] 1. Starting session for:', outcomeId);
  
  const outcome = await getOutcome(outcomeId);
  console.log('[DEBUG] 2. Got outcome:', outcome?.id);
  
  if (!outcome) {
    console.log('[DEBUG] 2a. Outcome not found, returning early');
    return;
  }
  
  const session = await createSession(outcome);
  console.log('[DEBUG] 3. Created session:', session?.id);
  
  await notifyUI(session);
  console.log('[DEBUG] 4. UI notified');
}

Isolation techniques:

  • Add strategic logging at entry/exit points
  • Check if issue is in frontend, backend, or IPC
  • Verify data at each boundary
  • Test with minimal reproduction case

Phase 3: Form Hypothesis

Based on evidence, form specific hypotheses:

## Hypothesis Log

### H1: IPC handler not registered
- Evidence: Console shows "invoke" called but no response
- Test: Add logging to main process IPC handler
- Result: ❌ Handler is registered

### H2: Promise not awaited
- Evidence: Function returns before async work completes
- Test: Add await to database call
- Result: ✅ Missing await found!

Read the full file on GitHub · 338 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. yesterday First seen · 338 lines · 52 tokens per session scan A cd89aa8fb38f

Subscribe to this mod's changes

debugging is a skill published in the GitHub repository macromania/agentop (10 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 1,988 once invoked, about $0.0003 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.