debug

A structured process for diagnosing software problems by reproducing them, narrowing their location, finding the root cause, and applying a fix. It uses error messages, recent changes, inputs, dependencies, and application state as evidence.

In plain words
What is it for?
Investigating bugs, crashes, unexpected behavior, performance issues, error messages, and tests that fail.
Why use it?
Guessing at fixes can hide the real problem or create new ones. This process turns vague symptoms and failing tests into a specific, testable cause.

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/viknesh20-20/claude-code-tool-kit/debug
Any agent
npx skills add viknesh20-20/claude-code-tool-kit --skill debug
Clone the repo
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kit

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 792 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 $0.00036 $0.00792
Opus 5 $0.00018 $0.00396
Sonnet 5 $0.00007 $0.00158
Haiku 4.5 $0.00004 $0.00079

Measured 2d ago against content hash a1c387254c5e, 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.

.claude/skills/debug/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structured Debugging

Recent Changes

!git log --oneline -10 2>/dev/null !git diff --stat HEAD~3 2>/dev/null


Debugging Process

Step 1: Gather Information

  1. What is the symptom? — Error message, unexpected behavior, crash, performance issue
  2. When did it start? — Check recent commits: git log --oneline -20
  3. Is it reproducible? — Always, sometimes, only in certain environments?
  4. What changed? — Recent code changes, dependency updates, config changes

Step 2: Read the Error

If there's an error message or stack trace:

  1. Read the full error message — don't skip parts
  2. Identify the origin — which file and line threw the error?
  3. Trace the call stack — how did execution reach that point?
  4. Check for root cause vs symptom — the first error in the chain is usually the cause

Step 3: Isolate the Problem

Use a binary search strategy:

  1. Narrow the scope: Is the issue in the frontend, backend, database, or external service?
  2. Check inputs: Are the inputs to the failing function correct?
  3. Check dependencies: Are all required services/modules available?
  4. Check state: Is the application/database in the expected state?
  5. Check environment: Are env vars, configs, and versions correct?

Step 4: Common Debugging Patterns

"It works on my machine"
  • Check environment variables
  • Check dependency versions (lock file differences)
  • Check OS/runtime version differences
  • Check file path separators (Windows vs Unix)
  • Check timezone/locale differences
"It worked yesterday"
  • git bisect to find the breaking commit
  • Check for dependency updates (lock file changes)
  • Check for infrastructure/config changes
  • Check for data changes in the database
"It works sometimes"
  • Race condition — look for shared mutable state
  • Timing issue — look for missing awaits, unhandled promises
  • Resource exhaustion — connections, file handles, memory
  • External dependency flakiness — network, API rate limits

Read the full file on GitHub · 89 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 · 89 lines · 36 tokens per session scan A a1c387254c5e

Subscribe to this mod's changes

debug is a skill published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 792 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 2026-08-31.

Related

Other skills, from other repositories

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

interview

Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.

Hmbown/CodeWhale · 40 tokens

security-review

Review trust boundaries, auth/authz, injection, secrets, filesystem/network exposure, dependencies, and exploitability without pretending a shallow lint is an audit.

Hmbown/CodeWhale · 33 tokens

ppt-review

Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.

Orkas-AI/Orkas · 2 tokens

ui-design-contract

Use this skill before rendering when the direction must persist across multiple screens/components, brand or system work, conflicting references, formal handoff, or a genuinely vague visual system. Ordinary single-screen screenshots and clear briefs use ui-design-executor's compact source/visual thesis instead of…

Orkas-AI/Orkas · 3 tokens

helmor-debug-operate

Operate, reproduce, and debug a running local Helmor desktop development build through the Tauri MCP bridge. Use when the user asks to use Tauri MCP, towery MCP, the local dev build, the Tauri webview, visual end-to-end validation, UI automation, screenshots, DOM/accessibility snapshots, IPC or log tracing…

dohooo/helmor · 117 tokens