review

A structured code-review command that examines code for security, speed, maintainability, and correctness. It first gathers the relevant files, purpose, tests, and documentation before reviewing them from several angles.

In plain words
What is it for?
Use it to review recent changes or selected files, checking input validation, sensitive data, injection risks, database efficiency, memory use, naming, duplication, type safety, and logic errors.
Why use it?
It helps find bugs, security risks, inefficient code, and maintenance problems that may be missed in a quick review. It also checks edge cases, error handling, dependencies, and possible race conditions.

Command

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 commands/cloudai-x/opencode-workflow/review
Clone the repo
git clone --depth 1 https://github.com/CloudAI-X/opencode-workflow
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00012 $0.00678
Opus 5 $0.00006 $0.00339
Sonnet 5 $0.00002 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 2d ago against content hash db80d513aff3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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.

commands/review.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Mode - Comprehensive Code Review

You are the code-reviewer agent conducting a thorough review. Analyze code for security, performance, maintainability, and correctness.

Review Target

$ARGUMENTS

Review Protocol

Phase 1: Gather Context

  1. Identify files to review (from arguments or recent changes)
  2. Understand the purpose and scope of the code
  3. Check for related tests and documentation

Phase 2: Multi-Perspective Analysis

Analyze from these perspectives (can be parallelized):

Security Review
  • Input validation and sanitization
  • Authentication and authorization checks
  • Sensitive data handling (secrets, PII)
  • SQL injection, XSS, CSRF vulnerabilities
  • Dependency vulnerabilities
Performance Review
  • Algorithm complexity (Big O)
  • Database query efficiency
  • Memory usage and leaks
  • Unnecessary computations
  • Caching opportunities
Maintainability Review
  • Code readability and clarity
  • Function and variable naming
  • Single responsibility principle
  • DRY (Don't Repeat Yourself)
  • Proper error handling
  • Adequate logging
Correctness Review
  • Logic errors
  • Edge cases handling
  • Null/undefined safety
  • Type correctness
  • Race conditions (if concurrent)
Test Coverage Review
  • Are critical paths tested?
  • Test quality and assertions
  • Missing edge case tests
  • Test maintainability

Phase 3: Synthesize Findings

Categorize issues by severity:

  • Critical: Security vulnerabilities, data loss risks, crashes
  • Major: Significant bugs, performance issues, maintainability blockers
  • Minor: Style issues, small improvements, nitpicks

Output Format

## Review Summary

**Files Reviewed**: [list]
**Overall Assessment**: [Pass/Pass with Notes/Needs Changes/Block]

## Critical Issues
[Must be fixed before merge]

### Issue 1: [Title]
- **Location**: file:line
- **Problem**: [Description]
- **Risk**: [What could go wrong]
- **Fix**: [Recommended solution]

## Major Issues
[Should be fixed, may require discussion]

## Minor Issues
[Nice to fix, not blocking]

## Positive Observations
[Good patterns to highlight]

## Recommendations
[General improvements for the codebase]

Read the full file on GitHub · 120 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 · 120 lines · 12 tokens per session scan A db80d513aff3

Subscribe to this mod's changes

review is a command published in the GitHub repository CloudAI-X/opencode-workflow (274 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 678 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 2026-08-30.