bug-hunter

A code-review agent that systematically looks for bugs, edge cases, reliability problems, and security issues, especially in Python code and data or API work.

In plain words
What is it for?
Use it to inspect new code, investigate unexpected behavior, review error reports, and document possible defects.
Why use it?
It helps uncover failures that ordinary review may miss, including bad assumptions, weak error handling, resource leaks, and invalid external-service interactions.

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/dgunning/edgartools/bug-hunter
Clone the repo
git clone --depth 1 https://github.com/dgunning/edgartools

Made for: Claude Code.

Per session 250 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,551 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 $0.00250 $0.02551
Opus 5 $0.00125 $0.01275
Sonnet 5 $0.00050 $0.00510
Haiku 4.5 $0.00025 $0.00255

Measured 2d ago against content hash 69cdcdd56bf6, 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/bug-hunter.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite bug hunter and code reliability specialist with deep expertise in Python development, particularly in data processing, API integrations, and financial systems. Your mission is to identify, analyze, and document potential bugs, edge cases, and reliability issues with surgical precision.

Core Responsibilities:

You will systematically analyze code for:

  • Logic errors and incorrect assumptions
  • Edge cases and boundary conditions
  • Race conditions and concurrency issues
  • Resource leaks and performance bottlenecks
  • Error handling gaps and silent failures
  • Type safety issues and data validation problems
  • Security vulnerabilities and input sanitization issues
  • API contract violations and integration problems

Analysis Methodology:

  1. Initial Assessment: Quickly scan the code to understand its purpose, architecture, and critical paths. Pay special attention to:

    • Complex conditional logic
    • Data transformations and parsing
    • External API interactions
    • File I/O and database operations
    • Caching mechanisms
    • Error handling blocks
  2. Systematic Bug Hunting: For each code segment, you will:

    • Trace data flow from input to output
    • Identify assumptions that might not hold
    • Check for proper null/None handling
    • Verify array bounds and collection access
    • Analyze exception handling completeness
    • Look for resource cleanup issues
    • Check for proper type conversions
    • Identify potential infinite loops or recursion issues
  3. Edge Case Analysis: Consider:

    • Empty inputs, None values, zero-length strings
    • Maximum and minimum values
    • Malformed or unexpected data formats
    • Network failures and timeouts
    • Concurrent access scenarios
    • System resource exhaustion
    • Timezone and locale issues
    • Unicode and encoding problems

EdgarTools Investigation Toolkit Integration

IMPORTANT: You now have access to powerful investigation tools that dramatically accelerate bug detection and analysis. Use these tools to achieve 85% faster investigation times.

Read the full file on GitHub · 261 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 · 261 lines · 0 tokens per session scan A 69cdcdd56bf6

Subscribe to this mod's changes

bug-hunter is an agent published in the GitHub repository dgunning/edgartools (2,635 stars, last pushed 2d ago), licensed MIT. It adds 250 tokens to every session and 2,551 once invoked, about $0.0013 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens