debugging

A structured method for investigating software bugs and unexpected behavior. It works through reproducing the problem, isolating its cause, fixing it, and validating the result.

In plain words
What is it for?
Use it for broken features, failing tests, regressions, errors, or any case where code behaves differently from what was expected.
Why use it?
It prevents guesses and premature code changes by requiring evidence that the cause is understood and that the fix does not create regressions.

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

Made for: Claude Code, Codex.

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 609 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 $0.00071 $0.00609
Opus 5 $0.00036 $0.00304
Sonnet 5 $0.00014 $0.00122
Haiku 4.5 $0.00007 $0.00061

Measured yesterday against content hash 2edcefe77471, 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.

skills/debugging/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugging & Investigation

4-Step Framework: Reproduce → Isolate → Fix → Validate

  • Never skip to Fix. Most wrong fixes come from jumping straight to code changes.
  • Reproduce: Run the faulty scenario. Note the exact error and conditions.
  • Isolate: Narrow down the failing component. 80% of bugs live in recently modified code — start there. Compare against working code. Find similar functionality that works and diff against the broken code.
  • Validate: Run the full test suite. Confirm the error is gone AND no regressions introduced.

Validate Before Fixing

  • Confirm root cause before proposing code changes. One hypothesis at a time — test the most likely first.
  • Explain root cause in writing (file path, line number, actual vs expected behavior) before proposing code changes.
  • Test means run code, not reason in your head. Execute a command, write a failing test, or check real output.
  • Read the user's evidence first. Study screenshots/errors before forming hypotheses. The answer is usually visible.
  • Add console.error to trace actual behavior when reasoning about what code "should" do isn't working. Reading code is not observing behavior.
  • Red flag phrases. Catch yourself saying "This should work", "Let me just try...", or "Quick fix for now" — stop and re-evaluate. You're guessing.

Anti-Loop Protocol

  • Each attempt MUST use a different diagnosis. If attempt 1 failed, don't vary the fix — vary the diagnosis. Two attempts targeting the same component with the same assumption count as one diagnosis, even if the code changes differ.
  • After 2 failed fix attempts, STOP. State what you tried, what each ruled out, and ask the user for context. If the user says "still broken" twice, you've failed twice.
  • Clear polluted context. After hitting the limit, recommend /clear — failed attempts in context actively degrade subsequent reasoning.
  • Watch for oscillation. Fixing A breaks B and vice versa = contradictory constraints. Stop and surface the conflict.
  • Revert as escape hatch. When debugging spirals, revert to last known good commit rather than stacking fixes on failed attempts.

Read the full file on GitHub · 32 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 · 32 lines · 71 tokens per session scan A 2edcefe77471

Subscribe to this mod's changes

debugging is a skill published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 609 once invoked, about $0.0004 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

memory

Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file.

memvid/claude-brain · 21 tokens

bearing-diagnosis

Complete bearing fault diagnostic workflow using vibration analysis and the predictive-maintenance-mcp server. Use this skill when the user says "diagnose bearing", "bearing fault", "bearing check", "detect bearing damage", "bearing vibration analysis", "inner race fault", "outer race fault", "ball defect", "cage…

LGDiMaggio/predictive-maintenance-mcp · 93 tokens

prognostics

Prognostic assessment workflow: trend analysis, degradation onset detection, and Remaining Useful Life (RUL) estimation using the predictive-maintenance-mcp server. Use this skill when the user says "trend analysis", "degradation trend", "RUL", "remaining useful life", "prognosis", "prognostics", "failure prediction"…

LGDiMaggio/predictive-maintenance-mcp · 120 tokens

signal-management

Signal loading, generation, and cache management using the predictive-maintenance-mcp server. Use this skill when the user says "load signal", "import signal", "list signals", "available signals", "generate test signal", "create test data", "synthetic signal", "clear cache", "signal info", "what signals are loaded"…

LGDiMaggio/predictive-maintenance-mcp · 91 tokens

anomaly-detection

ML-based anomaly detection and model training for vibration signals using the predictive-maintenance-mcp server. Use this skill when the user says "anomaly detection", "train model", "detect anomalies", "outlier detection", "normal vs abnormal", "machine learning", "one-class SVM", "LOF", "local outlier factor"…

LGDiMaggio/predictive-maintenance-mcp · 100 tokens

gear-diagnosis

Gear fault diagnosis workflow using vibration analysis via the predictive-maintenance-mcp server. Use this skill when the user says "gear fault", "gear diagnosis", "gear mesh", "gearbox analysis", "gear vibration", "tooth damage", "gear defect", "diagnose gear", "gear mesh frequency", "sideband analysis", or wants to…

LGDiMaggio/predictive-maintenance-mcp · 78 tokens