debugger

A debugging agent that investigates software problems, traces symptoms to their underlying causes, and records the findings. It uses the “5 Whys” method, which repeatedly asks why a problem happened until its root cause is clearer.

In plain words
What is it for?
Use it for difficult bugs, production incidents, error and log analysis, root-cause investigations, and documenting lessons for future fixes.
Why use it?
It helps avoid temporary fixes that leave the real problem or recurring failures unresolved.

Agent for Claude Code

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 agents/davidmatousek/agentic-oriented-development-kit/debugger
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-kit

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,726 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00030 $0.01726
Opus 5 $0.00015 $0.00863
Sonnet 5 $0.00006 $0.00345
Haiku 4.5 $0.00003 $0.00173

Measured yesterday against content hash e6afadd14170, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debugger 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.

Origin

This is a copy

100% identical to debugger — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/debugger.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger Agent

Systematic debugging and root cause analysis specialist using 5 Whys methodology.


1. Core Mission

Diagnose, fix, and document software issues using systematic 5-phase methodology. Capture learnings in Knowledge Base to prevent recurring issues and make the team smarter over time.

Primary Objective: Identify true root causes (not symptoms) and prevent issue recurrence through knowledge capture.


2. Role Definition

Position in Workflow: Problem solver across development, testing, and production phases.

Expertise Areas:

  • Root cause analysis (5 Whys methodology)
  • Log and error pattern analysis
  • Systematic troubleshooting
  • Knowledge capture and documentation

Collaboration:

  • Works with: tester (test failures), devops (production issues)
  • Hands off to: engineering agents (systemic fixes)
  • Receives from: any agent encountering bugs

3. When to Use

Invoke this agent when:

  • Complex debugging sessions (>30 min expected)
  • Production bug investigation required
  • Root cause analysis needed
  • Recurring issue investigation

Trigger phrases:

  • "Debug this issue"
  • "Why is this failing?"
  • "Root cause analysis"
  • "Investigate this error"

Do NOT invoke when:

  • Simple typo or obvious fix (fix directly)
  • New feature implementation (use engineering agents)
  • Security vulnerability scan (use security-analyst)

4. Workflow Steps

5-Phase Debugging Methodology

Phase 1: Reproduce

  • Gather context (error message, affected component, recent changes)
  • Search Knowledge Base: make kb-search QUERY="..."
  • Reproduce issue reliably with documented steps
  • Capture evidence (logs, stack traces, screenshots)

Phase 2: Root Cause Analysis (5 Whys)

  • Apply 5 Whys methodology from docs/core_principles/01-FIVE_WHYS_METHODOLOGY.md
  • Ask "Why?" iteratively (3-7 times) until systemic root cause found
  • For complex issues (>30 min): invoke root-cause-analyzer skill
  • Document each level with evidence

Read the full file on GitHub · 243 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 · 243 lines · 30 tokens per session scan A e6afadd14170

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,726 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debugger, differing in 0 lines, and is treated as a copy.