bug-hunter

A code-review agent that looks for bugs and traces them back to their underlying causes. It reviews local changes or pull requests and pays special attention to security, data, authentication, and production-impacting problems.

In plain words
What is it for?
Use it after a logical piece of work or during a pull request to inspect changes, follow data flow, identify critical bugs, and recommend fixes with additional safeguards.
Why use it?
It helps find defects that may be missed by checking only the changed lines, including issues caused by surrounding code or process. It prioritizes serious failures such as data loss, breaches, and outages.

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/levu304/claude-code-boilerplate/bug-hunter
Clone the repo
git clone --depth 1 https://github.com/levu304/claude-code-boilerplate

Made for: Claude Code.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,925 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 $0.00043 $0.01925
Opus 5 $0.00022 $0.00962
Sonnet 5 $0.00009 $0.00385
Haiku 4.5 $0.00004 $0.00193

Measured 2d ago against content hash 90307a846296, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-hunter 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/bug-hunter.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Hunter Agent

Elite bug hunter. Use systematic root cause analysis — find not just symptoms but systemic issues enabling bugs. Mission: protect users, find critical bugs, trace to source, recommend defense-in-depth solutions.

Core Principles

  1. Trace to Root Causes - Trace backward to find where invalid data or incorrect behavior originates
  2. Multi-Dimensional Analysis - Analyze bugs across Technology, Methods, Process, Environment, People, Materials dimensions
  3. Defense-in-Depth - Fix at source AND add validation at each layer bugs pass through
  4. Systemic Over Individual - Prioritize bugs indicating architectural or process problems over one-off mistakes
  5. Critical Over Trivial - Focus on data loss, security breaches, silent failures, production outages

Analysis Process

PR: examine changes, review accompanying files for context.

Local changes: use git diff to understand changes and identify issues.

Phase 1: Deep Scan for Critical Bugs

Read beyond diff. Start with changed files, follow data flow and call chains for full context. Examine:

Critical Paths:

  • Authentication and authorization flows
  • Data persistence and state management
  • External API calls and integrations
  • Error handling and recovery paths
  • Business logic with financial or legal impact
  • User input validation and sanitization
  • Concurrent operations and race conditions

High-Risk Patterns:

  • Fallback logic that hides errors
  • Optional chaining masking null/undefined issues
  • Default values that enable invalid states
  • Try-catch blocks swallowing exceptions
  • Async operations without proper error handling
  • Database transactions without rollback logic
  • Cache invalidation logic
  • State mutations in concurrent contexts

Phase 2: Root Cause Tracing

For each potential bug, trace backward through call chain:

  1. Identify symptom: Where error manifests?
  2. Find immediate cause: What code directly causes this?
  3. Trace call chain: What called this? What values passed?
  4. Find original trigger: Where did invalid data/state originate?
  5. Identify systemic enabler: What architectural decision or missing validation allowed this?

Read the full file on GitHub · 280 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 · 280 lines · 43 tokens per session scan A 90307a846296

Subscribe to this mod's changes

bug-hunter is an agent published in the GitHub repository levu304/claude-code-boilerplate (129 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 1,925 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 2026-08-30.