subagent CX Codex

incident-response-code-reviewer — Claude Code subagent: what it does

Q: How to install incident-response-code-reviewer in Claude Code?

Run `/plugin marketplace add wshobson/agents` and then execute `/plugin install incident-response@claude-code-workflows`. You can also configure it manually by adding `.claude/agents/code-reviewer.md`.

Q: Which model does this subagent require?

The agent configuration explicitly specifies the `sonnet` model.

Finds logic flaws and unhandled errors during code reviews. Suggests minimal fixes and rates severity across the repository.

Install into Claude Code · Plugin marketplace All methods and platforms ↓

/plugin marketplace add wshobson/agents
/plugin install incident-response@claude-code-workflows

Open on GitHub

What incident-response-code-reviewer does

The subagent runs on sonnet and follows a structured seven-step audit path. It inspects algorithms for flawed assumptions and audits boundary contracts. Once local issues are clear, it searches the repository for duplicate vulnerability patterns.

Instead of suggesting broad refactoring, the reviewer focuses on the smallest effective patch. That keeps hotfixes safe during an ongoing incident. Every report includes severity ratings and readiness checks.

Dynamic code without explicit type signatures will trigger immediate warnings during analysis.

What it helps with

Detect logic errors and missing edge cases in code paths
Spot unhandled promises, panics, and missing error checks
Search the repository for identical vulnerability patterns
Design minimal safe hotfixes with severity ratings

Example prompts for the agent

Review this payment handler for logic errors and type safety gaps
Search the project for similar input validation vulnerabilities
Assess whether this hotfix is ready for deployment and suggest a minimal patch

How to install incident-response-code-reviewer

1Plugin marketplace

/plugin marketplace add wshobson/agents

/plugin install incident-response@claude-code-workflows

2Manually: put the files in place

.claude/agents/code-reviewer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Manually: put the files in place

.codex/agents/code-reviewer.toml

Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

Manually: put the files in place

.cursor/agents/code-reviewer.md

Cursor also reads .claude/agents/

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about incident-response-code-reviewer

How to install incident-response-code-reviewer in Claude Code?

Run /plugin marketplace add wshobson/agents and then execute /plugin install incident-response@claude-code-workflows. You can also configure it manually by adding .claude/agents/code-reviewer.md.

What does incident-response-code-reviewer do?

It reviews code for algorithmic mistakes, contract violations, and missing try-catch blocks. After analyzing the code, it suggests targeted patches and rates issue severity.

Which model does this subagent require?

The agent configuration explicitly specifies the sonnet model.

Source text

code-reviewer.md · MIT

---
name: incident-response-code-reviewer
description: Reviews code for logic flaws, type safety gaps, error handling issues, architectural concerns, and similar vulnerability patterns. Provides fix design recommendations.
model: sonnet
---

You are a code review specialist focused on identifying logic flaws and design issues in codebases.

## Purpose

Perform thorough code reviews to find logic errors, type safety gaps, missing error handling, and architectural concerns. You identify similar vulnerability patterns across the codebase and recommend minimal, effective fixes.

## Capabilities

- Logic flaw analysis: incorrect assumptions, missing edge cases, wrong algorithms
- Type safety review: where stronger types could prevent issues
- Error handling audit: missing try-catch, unhandled promises, panic scenarios
- Contract validation: input validation gaps, output guarantees not met
- Architecture review: tight coupling, missing abstractions, layering violations
- Pattern detection: find similar vulnerabilities across the codebase
- Fix design: minimal change vs refactoring vs architectural improvement
- Final approval review: code quality, security, deployment readiness

## Response Approach

1. Analyze the code path and identify logic flaws
2. Check type safety and where stronger types help
3. Audit error handling for gaps
4. Validate contracts and boundaries
5. Look for similar patterns elsewhere in the codebase
6. Design the minimal effective fix
7. Provide a structured review with severity ratings

Similar subagents

All subagents for Code review and refactoring →

code-reviewer official Anthropic Reviews code changes against CLAUDE.md project rules and flags material defects. Run it before a commit or pull request. 31,050installs code-reviewer official Anthropic This subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. 31,050installs security-auditor official Anthropic This subagent searches code for security flaws and gives engineers concrete fixes. Use it to review a project before hardening or modernization work. 10,718installs test-engineer official Anthropic This subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. 9,715installs code-reviewer VoltAgent Community Reviews code changes for bugs, security flaws and maintenance issues. Use it before merging complex work or auditing a project. 31,050installs debugger VoltAgent Community Diagnoses software failures, reads stack traces, and isolates root causes to fix elusive bugs. Helpful when logs alone do not explain a crash. 13,459installs

From the same set508

The whole set →