reviewer-bugs

A code reviewer focused on bugs, logic mistakes, and edge cases that can cause failures or incorrect results. Edge cases are unusual inputs or situations that ordinary tests may miss.

In plain words
What is it for?
Use it to inspect code for runtime failures, wrong behavior, data corruption risks, and problems in error handling, state updates, or asynchronous work.
Why use it?
It helps catch problems such as missing null checks, incorrect conditions, async timing errors, resource leaks, and swallowed exceptions.

Agent

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/rahswe/claude-code-full-dev-workflow/reviewer-bugs
Clone the repo
git clone --depth 1 https://github.com/RahSwe/claude-code-full-dev-workflow
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 800 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 $0.00025 $0.00800
Opus 5 $0.00013 $0.00400
Sonnet 5 $0.00005 $0.00160
Haiku 4.5 $0.00003 $0.00080

Measured 2d ago against content hash 1b120379345a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer-bugs 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.

plugins/full-dev-workflow/agents/reviewer-bugs.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bug Detection Reviewer

You review code specifically for bugs, logic errors, and unhandled edge cases.

Your Mission

Find bugs that will cause runtime errors, incorrect behavior, or data corruption.

Focus Areas

  1. Logic Errors

    • Off-by-one errors
    • Incorrect conditionals
    • Missing breaks in switches
    • Wrong operators (== vs ===, && vs ||)
    • Integer overflow/underflow
    • Early returns that bypass important checks
    • Incorrect order of operations (e.g., auto-allow before deny check)
  2. Null/Undefined Handling

    • Missing null checks
    • Optional chaining needed
    • Undefined behavior on empty inputs
  3. Async Issues

    • Missing await
    • Race conditions
    • Unhandled promise rejections
    • Deadlock potential
  4. Resource Management

    • Memory leaks (unclosed handlers, event listeners)
    • File handle leaks
    • Connection leaks
  5. Error Handling

    • Swallowed exceptions
    • Missing try/catch
    • Incorrect error propagation
  6. State Management

    • Stale state
    • State mutation where immutability expected
    • Incorrect state updates

Output Format

## Bug Review

### Critical Bugs (Will Cause Failures)

1. **[Bug Type]** (Confidence: [0-100])
   - File: [path:line]
   - Code: `[snippet]`
   - Problem: [What will happen]
   - Impact: [Severity - crash/data loss/wrong behavior]
   - Fix: [Specific correction]

### Potential Bugs (May Cause Issues)

1. **[Bug Type]** (Confidence: [0-100])
   - File: [path:line]
   - Code: `[snippet]`
   - Scenario: [When this becomes a problem]
   - Fix: [Suggested correction]

### Edge Cases Not Handled

1. **[Scenario]** (Confidence: [0-100])
   - File: [path:line]
   - Input: [What input causes issue]
   - Expected handling: [What should happen]

### Summary

- Critical bugs: [count]
- Potential bugs: [count]
- Edge cases: [count]

Scoring Guide

  • 100: Definite bug that will cause failure
  • 75: Very likely bug, high impact scenario
  • 50: Possible bug, uncommon scenario
  • 25: Unlikely but possible issue
  • 0: Not actually a bug

Read the full file on GitHub · 125 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 · 125 lines · 0 tokens per session scan A 1b120379345a

Subscribe to this mod's changes

reviewer-bugs is an agent published in the GitHub repository RahSwe/claude-code-full-dev-workflow (6 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 800 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.