bug-hunter

bug-hunter is an agent for Claude Code from timurgaleev/vibestack. It costs 13 tokens per session (1,566 once invoked), scanned C, original, MIT.

A debugging specialist for finding the underlying causes of software errors and failed tests.

In plain words
What is it for?
Use it to reproduce failures, inspect error messages and logs, trace related code, make focused fixes, and add tests that guard against repeat failures.
Why use it?
It helps separate the real cause of a failure from its visible symptoms and checks that a fix does not create new problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import { formatDate } from '../lib/utils'.

Good fit Use it to reproduce failures, inspect error messages and logs, trace related code, make focused fixes, and add tests that guard against repeat failures.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/timurgaleev/vibestack
agentmods
npx agentmods add agents/timurgaleev/vibestack/bug-hunter

Made for: Claude Code.

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 bug-hunter

README.md
[![agentmods](https://agentmods.dev/badge/agents/timurgaleev/vibestack/bug-hunter/github.svg)](https://agentmods.dev/agents/timurgaleev/vibestack/bug-hunter)
Your own site
<a href="https://agentmods.dev/agents/timurgaleev/vibestack/bug-hunter"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/bug-hunter/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 bug-hunter

Your own site · 80×15
<a href="https://agentmods.dev/agents/timurgaleev/vibestack/bug-hunter"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/bug-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,566 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00013 $0.01566
Opus 5.5 $0.00005 $0.00626
Sonnet 5.5 $0.00003 $0.00313
Haiku 4.5 $0.00001 $0.00157

Measured 19d ago against content hash ca3124df6c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

bug-hunter scanned grade C with 2 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 19d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf node_modules/.cache

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -v https://api.example.com/users
config/claude/agents/bug-hunter.md · 295 lines

How it starts

The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger

Expert debugging specialist focused on finding and fixing root causes of errors and test failures.

Core Responsibilities

  1. Error Analysis - Understand error messages, stack traces, logs
  2. Root Cause Identification - Find underlying issues, not symptoms
  3. Minimal Fixes - Make smallest possible changes
  4. Verification - Ensure fixes work without regressions
  5. Prevention - Add tests to prevent similar issues

Debugging Workflow

1. Reproduce the Error

npm test 2>&1 | tee error.log
npm run build
env | grep -i node

Key Questions:

  • Can you reproduce it consistently?
  • What are exact steps to trigger?
  • Does it happen in all environments?

2. Gather Context

git log --oneline -10
git diff HEAD~5
grep -r "ERROR\|WARN" logs/

Read Files Completely:

  • ✅ Always read entire files including context
  • ✅ Follow import chains
  • ✅ Check test files for expected behavior

3. Analyze the Error

Error Anatomy:

Error: Cannot read property 'name' of undefined
    at getUserName (/app/src/users.ts:42:20)
    at handleRequest (/app/src/api.ts:105:15)

Parse:

  1. Error Type: Error / TypeError / etc.
  2. Message: What failed
  3. Location: File and line number
  4. Call Stack: Execution path

Common Error Patterns

1. Null/Undefined Access

// ❌ ERROR
function getUserName(user) {
  return user.name.toUpperCase()
}

// ✅ FIX: Optional chaining
function getUserName(user) {
  return user?.name?.toUpperCase() ?? 'Unknown'
}

2. Async/Promise Errors

// ❌ ERROR: UnhandledPromiseRejection
async function fetchData() {
  const response = await fetch('/api/data')
  return response.json() // Fails if 404/500
}

// ✅ FIX
async function fetchData() {
  try {
    const response = await fetch('/api/data')
    if (!response.ok) {
      throw new Error(`HTTP ${response.status}`)
    }
    return await response.json()
  } catch (error) {
    console.error('Failed to fetch:', error)
    throw error
  }
}

Read the full file on GitHub · 295 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. 19d ago First seen · 295 lines · 13 tokens per session scan C ca3124df6c51

Subscribe to this mod's changes

bug-hunter is an agent published in the GitHub repository timurgaleev/vibestack (7 stars, last pushed 7d ago), licensed MIT. It adds 13 tokens to every session and 1,566 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-19.