Bug Hunter — Data & AI agent for Claude Code
Bug detection specialist.
How to install Bug Hunter
Installs to ~/.claude/agents/dykyi-roman-awesome-claude-code-bug-hunter.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dykyi-roman/awesome-claude-code/HEAD/agents/bug-hunter.md -o ~/.claude/agents/dykyi-roman-awesome-claude-code-bug-hunter.md Restart Claude Code, or start a new session, for it to be picked up.
What Bug Hunter does
name: bug-hunter description: Bug detection specialist. Finds logic errors, null pointers, boundary issues, race conditions, resource leaks, exception issues, type issues, SQL injection, infinite loops. Use PROACTIVELY for code review bug detection. tools: Read, Grep, Glob model: opus skills: find-logic-errors, find-null-pointer-issues, find-boundary-issues, find-race-conditions, find-resource-leaks, find-exception-issues, find-type-issues, check-sql-injection, find-infinite-loops, discover-
Alternatives in Data & AI
- Read Research For Nyquist Validation Data — cat "$phase_dir"/-RESEARCH.md 2>/dev/null node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" roadmap get-pha 38.5k ★
- Credential Hunter — Autonomous credential-attack pipeline runner 4.5k ★
- LLM AI Hunter — LLM and Agentic AI vulnerability specialist 812 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Runtime Reviewer
Reviews a diff for what happens when it runs — empty and null data, error paths, leaks, races, re-renders, two
Swift Concurrency Expert
Swift Concurrency specialist. Use proactively when dealing with async/await, actors, Sendable conformance, Tas
Sqli Hunter
Active SQL injection hunter for an ingested program. Consumes webvuln-surface injection points + auth-context,
Marketing Growth Hacker
Expert growth strategist specializing in rapid user acquisition through data-driven experimentation. Develops
Reviewer Correctness
Correctness specialist reviewer. Verifies code actually works as intended: intent-implementation alignment, in
Budgeter
Resource gatekeeper. Other agents must call the budgeter before launching long-running training, expensive LLM
Related Skills
Concurrency Atomicity
Run a concurrency-correctness and atomicity review against a diff, PR, or branch — race conditions, TOCTOU, de
Modes
When updating your task boundary, you must explicitly set your current agent mode. Think of this as a way of f
Sanyuan Skills
Expert code review skill: SOLID, security, performance, error handling, boundary conditions.
