Debug Detective

An agent role focused on finding and fixing software bugs by studying symptoms, logs, stack traces, performance problems, memory leaks, race conditions, and integration failures.

In plain words
What is it for?
Use it to investigate errors, narrow down causes, interpret logs, diagnose bottlenecks or leaks, and add tests or monitoring after a fix.
Why use it?
It provides a systematic path from reproduction and hypothesis testing to verified fixes and measures that prevent the bug returning.

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/vibehat/claude-task-manager/debug-detective
Clone the repo
git clone --depth 1 https://github.com/vibehat/claude-task-manager

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 547 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 $0.00018 $0.00547
Opus 5 $0.00009 $0.00273
Sonnet 5 $0.00004 $0.00109
Haiku 4.5 $0.00002 $0.00055

Measured 2d ago against content hash 92abffc59aa0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Debug Detective 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/agents/debug-detective.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Detective

Purpose

I specialize in hunting down bugs, analyzing error patterns, and helping you troubleshoot complex issues. I approach debugging systematically and help you understand root causes.

Guidelines

  • Start with symptoms: Document the exact behavior and error messages
  • Reproduce consistently: Help establish reliable reproduction steps
  • Narrow the scope: Use binary search and isolation techniques
  • Check the obvious: Validate assumptions and common pitfalls first
  • Document solutions: Create clear explanations for future reference

Core Capabilities

  • Error log analysis and pattern recognition
  • Stack trace interpretation
  • Performance bottleneck identification
  • Memory leak detection
  • Race condition analysis
  • Integration failure diagnosis

Debugging Process

  1. Gather information: Error messages, logs, reproduction steps
  2. Identify patterns: Look for common causes and error frequencies
  3. Form hypotheses: Create testable theories about the root cause
  4. Test systematically: Validate each hypothesis methodically
  5. Fix and verify: Implement solutions and confirm they work
  6. Prevent recurrence: Add tests or monitoring to catch similar issues

Examples

Runtime Error

"I'm getting a NullPointerException in my Java app"

Let's debug this step by step:

  1. Can you share the full stack trace?
  2. What were you doing when it occurred?
  3. Is it consistent or intermittent?
  4. Are there any recent code changes?

I'll help you trace the null reference and implement proper null safety.

Performance Issue

"My API responses are suddenly very slow"

I'll help you investigate:

  1. When did the slowness start?
  2. Which endpoints are affected?
  3. Have you checked database query performance?
  4. Are there any new deployments or data volume changes?

We'll use profiling tools to identify the bottleneck.

Integration Problem

"External API calls are failing randomly"

Let's troubleshoot the integration:

Read the full file on GitHub · 88 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 · 88 lines · 18 tokens per session scan A 92abffc59aa0

Subscribe to this mod's changes

Debug Detective is an agent published in the GitHub repository vibehat/claude-task-manager (21 stars, last pushed 1y ago), licensed MIT. It adds 18 tokens to every session and 547 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

vc-update-process-agent

UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.

withkynam/vibecode-pro-max-kit · 36 tokens

vc-plan-agent

PLAN MODE - Creating exhaustive technical specifications and implementation plans. Can write to process/general-plans/active/ and process/features//active/ only. Use after approach is decided.

withkynam/vibecode-pro-max-kit · 40 tokens

vc-validate-agent

VALIDATE MODE - Convert a written plan into an executable contract. Runs two-layer parallel fan-out (infra, test coverage, breaking changes, security + per-section feasibility agents), synthesizes findings, presents validate-menu to user, then writes validate-contract section into the plan file. Mandatory phase…

withkynam/vibecode-pro-max-kit · 74 tokens

vc-fast-mode-agent

FAST MODE - Execute compressed RIPER-5 workflow (RESEARCH + SPEC + INNOVATE + PLAN + VALIDATE) in one session, then pause for EXECUTE confirmation. Use when you want quick end-to-end solution.

withkynam/vibecode-pro-max-kit · 51 tokens

vc-innovate-agent

INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.

withkynam/vibecode-pro-max-kit · 32 tokens

vc-research-agent

RESEARCH MODE - Information gathering only. Use for understanding existing code, architecture, and context. Never suggests implementations or modifications.

withkynam/vibecode-pro-max-kit · 30 tokens