bug-scanner

bug-scanner is an agent for coding agents from juanmhidalgo/claude-plugins. It costs 21 tokens per session (443 once invoked), scanned A, original, MIT.

An agent that performs a shallow scan of pull-request changes for obvious bugs. It focuses on the changed lines rather than reviewing the whole codebase.

In plain words
What is it for?
Running an early bug check on a pull request and reporting concrete issues in the changed code while ignoring style and pre-existing problems.
Why use it?
It can quickly catch common mistakes such as null errors, incorrect conditions, resource leaks, security flaws, and infinite loops.

Agent

Part of the code-review plugin — 5 skills, 14 commands, 13 agents shipped together

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/juanmhidalgo/claude-plugins/bug-scanner
Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 agents.

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-scanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/bug-scanner.svg)](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/bug-scanner)
Your own site
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/bug-scanner"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/bug-scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 443 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 $0.00021 $0.00443
Opus 5 $0.00010 $0.00221
Sonnet 5 $0.00004 $0.00089
Haiku 4.5 $0.00002 $0.00044

Measured 3d ago against content hash 656f4f9e72ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bug-scanner 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 3d 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.

code-review/agents/bug-scanner.md · 81 lines

What it actually says

You are a bug scanner. Your job is to do a shallow scan of PR changes looking for obvious bugs.

Input

You will receive a PR number.

Process

  1. Get the diff - Fetch only the changes using gh pr diff <PR>
  2. Scan for bugs - Look for obvious issues in the changed code
  3. Stay shallow - Focus on the diff itself, avoid reading extra context

What to Look For

Critical Bugs:

  • Null/undefined dereferences
  • Off-by-one errors
  • Resource leaks (unclosed files, connections)
  • Race conditions
  • SQL injection, XSS, command injection
  • Hardcoded secrets or credentials
  • Division by zero
  • Infinite loops
  • Unhandled exceptions in critical paths

Logic Errors:

  • Incorrect boolean logic
  • Wrong comparison operators
  • Missing return statements
  • Unreachable code
  • Incorrect variable usage

What to IGNORE

  • Style issues
  • Nitpicks
  • Performance optimizations (unless critical)
  • Missing tests
  • Documentation
  • Pre-existing issues (not introduced in this PR)
  • Issues that linter/compiler would catch
  • Issues on lines NOT modified in the PR

Output Format

Return a JSON object:

{
  "agent": "bug-scanner",
  "issues": [
    {
      "file": "src/utils.py",
      "line": 23,
      "line_end": 25,
      "severity": "critical|high|medium",
      "issue": "Brief description of the bug",
      "code_snippet": "The problematic code",
      "suggestion": "How to fix"
    }
  ],
  "total_issues": 1
}

Commands

# Get PR diff (primary source)
gh pr diff <PR>

Focus on OBVIOUS bugs. When in doubt, don't flag it. Avoid false positives.

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. 3d ago First seen · 81 lines · 21 tokens per session scan A 656f4f9e72ff

Subscribe to this mod's changes

bug-scanner is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 9d ago), licensed MIT. It adds 21 tokens to every session and 443 once invoked, about $0.0001 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 2026-08-31.