Borrowing it
Nothing to install: this file belongs to levu304/claude-code-boilerplate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/levu304/claude-code-boilerplate/main/.claude/agents/bug-hunter.mdgit clone --depth 1 https://github.com/levu304/claude-code-boilerplateWrote 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.
[](https://agentmods.dev/agents/levu304/claude-code-boilerplate/bug-hunter)<a href="https://agentmods.dev/agents/levu304/claude-code-boilerplate/bug-hunter"><img src="https://agentmods.dev/badge/agents/levu304/claude-code-boilerplate/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.
<a href="https://agentmods.dev/agents/levu304/claude-code-boilerplate/bug-hunter"><img src="https://agentmods.dev/badge/agents/levu304/claude-code-boilerplate/bug-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.01925 |
| Opus 5.5 | $0.00017 | $0.00770 |
| Sonnet 5.5 | $0.00009 | $0.00385 |
| Haiku 4.5 | $0.00004 | $0.00193 |
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 2mo 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.
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
- Trace to Root Causes - Trace backward to find where invalid data or incorrect behavior originates
- Multi-Dimensional Analysis - Analyze bugs across Technology, Methods, Process, Environment, People, Materials dimensions
- Defense-in-Depth - Fix at source AND add validation at each layer bugs pass through
- Systemic Over Individual - Prioritize bugs indicating architectural or process problems over one-off mistakes
- 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:
- Identify symptom: Where error manifests?
- Find immediate cause: What code directly causes this?
- Trace call chain: What called this? What values passed?
- Find original trigger: Where did invalid data/state originate?
- Identify systemic enabler: What architectural decision or missing validation allowed this?
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.
- 2mo ago First seen · 280 lines · 43 tokens per session scan A 90307a846296
bug-hunter is an agent published in the GitHub repository levu304/claude-code-boilerplate (130 stars, last pushed 6mo ago), licensed MIT. It adds 43 tokens to every session and 1,925 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…