debug-assistant

debug-assistant is a command for Claude Code from rafaelkamimura/claude-tools. It costs 0 tokens per session (2,374 once invoked), scanned A, original, MIT.

A debugging assistant that examines errors, logs, stack traces, crashes, and reproduction details to help find their causes. A stack trace is the list of code calls that led to an error.

In plain words
What is it for?
Use it to analyse pasted errors or log files, investigate recent crashes, suggest fixes, trace root causes, and set up debugging environments.
Why use it?
It gives a structured way to collect the right context, connect symptoms to likely causes, and produce steps for reproducing the problem.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-tools plugin — 12 commands, 46 agents shipped together

Good fit Use it to analyse pasted errors or log files, investigate recent crashes, suggest fixes, trace root causes, and set up debugging environments.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rafaelkamimura/claude-tools/debug-assistant
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.

Clone the repo
git clone --depth 1 https://github.com/rafaelkamimura/claude-tools

Made for: Claude Code.

Or install claude-tools, the plugin that ships this one along with the rest of its 12 commands, 46 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for debug-assistant

README.md
[![agentmods](https://agentmods.dev/badge/commands/rafaelkamimura/claude-tools/debug-assistant/github.svg)](https://agentmods.dev/commands/rafaelkamimura/claude-tools/debug-assistant)
Your own site
<a href="https://agentmods.dev/commands/rafaelkamimura/claude-tools/debug-assistant"><img src="https://agentmods.dev/badge/commands/rafaelkamimura/claude-tools/debug-assistant/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for debug-assistant

Your own site · 80×15
<a href="https://agentmods.dev/commands/rafaelkamimura/claude-tools/debug-assistant"><img src="https://agentmods.dev/badge/commands/rafaelkamimura/claude-tools/debug-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.02374
Opus 5.5 $0.00000 $0.00950
Sonnet 5.5 $0.00000 $0.00475
Haiku 4.5 $0.00000 $0.00237

Measured 1mo ago against content hash 9b65ed08bf9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

debug-assistant 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 1mo 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.

commands/debug-assistant.md · 423 lines

How it starts

The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intelligent Debugging Helper

Advanced debugging assistant that analyzes errors, suggests fixes, traces root causes, and sets up debugging environments.

Purpose

  • Analyze error logs and stack traces
  • Suggest fixes based on error patterns
  • Set up debugging environments
  • Generate reproduction steps
  • Track down root causes with specialized agents

Workflow

Step 1: Error Input

  1. STOP → "How would you like to provide the error?"

    1. Paste error message/stack trace
    2. Point to log file
    3. Describe the issue
    4. Run failing command
    5. Analyze recent crashes
    
    Choose method (1-5):
    
  2. Context Gathering

    • STOP → "When did this error start? (timestamp/commit/today):"
    • STOP → "Is it reproducible? (always/sometimes/once):"
    • STOP → "What were you doing when it occurred?:"

Step 2: Error Analysis

  1. Parse Error Information

    // Extract key information
    const errorInfo = {
      type: "TypeError",
      message: "Cannot read property 'x' of undefined",
      file: "src/components/UserList.jsx",
      line: 45,
      column: 12,
      stack: [...],
      timestamp: "2024-01-15T10:30:00Z"
    };
    
  2. Categorize Error Type

    error_categories:
      - Runtime Errors:
        - TypeError
        - ReferenceError
        - RangeError
      - Async Errors:
        - Promise rejection
        - Callback errors
        - Race conditions
      - Network Errors:
        - Connection refused
        - Timeout
        - CORS issues
      - Build Errors:
        - Compilation failure
        - Module not found
        - Syntax errors
    
  3. Deploy Analysis Agents

    • debugger: Deep error analysis
    • backend-architect: System-level debugging
    • test-automator: Create reproduction test
    • performance-engineer: Performance-related issues

Step 3: Root Cause Analysis

  1. Trace Error Source
    # Git blame to find when introduced
    git blame -L 40,50 src/components/UserList.jsx
    
    # Check recent changes
    git log -p --since="2 days ago" src/components/UserList.jsx
    

Read the full file on GitHub · 423 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. 1mo ago First seen · 423 lines · 0 tokens per session scan A 9b65ed08bf9c

Subscribe to this mod's changes

debug-assistant is a command published in the GitHub repository rafaelkamimura/claude-tools (10 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,374 tokens. 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 commands, from other repositories