codereview

A structured process for reviewing code in several passes and classifying findings by severity and confidence.

In plain words
What is it for?
Use it to review specified files for security flaws, crashes, data loss, logic errors, reliability problems, code smells, and documentation gaps.
Why use it?
It reduces the chance of missing bugs during a quick review and separates critical problems from smaller maintainability or style issues.

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/krmcbride/claude-plugins/codereview
Clone the repo
git clone --depth 1 https://github.com/krmcbride/claude-plugins
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,230 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 $0.00014 $0.03230
Opus 5 $0.00007 $0.01615
Sonnet 5 $0.00003 $0.00646
Haiku 4.5 $0.00001 $0.00323

Measured yesterday against content hash 967e0b8f9eca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codereview 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 yesterday.

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.

essentials/commands/codereview.md · 482 lines

How it starts

The opening of the file, as written. The whole thing — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeReview Investigation Workflow

Conduct a systematic, multi-step code review of the specified files using the CodeReview methodology. This approach prevents superficial single-pass reviews by enforcing multiple investigation steps with progressive confidence building.

Files to review and focus: $ARGUMENTS

Code Review Framework

Severity Classification

Use this framework to classify every issue found:

  • 🔴 CRITICAL - Security vulnerabilities, crashes, data loss, data corruption
  • 🟠 HIGH - Logic errors, reliability problems, significant bugs
  • 🟡 MEDIUM - Code smells, maintainability issues, technical debt
  • 🟢 LOW - Style issues, minor improvements, documentation gaps

Confidence Levels

Track your confidence explicitly at each step using the TodoWrite tool. Progress through these levels as evidence accumulates:

  • exploring - Initial code scan, forming hypotheses about issues
  • low - Basic patterns identified, many areas unchecked
  • medium - Core issues found, edge cases need validation
  • high - Comprehensive coverage, findings validated
  • very_high - Exhaustive review, minor gaps only
  • almost_certain - All code paths checked
  • certain - Complete confidence, no further investigation needed

Investigation State

Maintain this state structure throughout the code review:

{
  "step_number": 2,
  "confidence": "medium",
  "findings": [
    "Step 1: Found SQL injection vulnerability in auth.py",
    "Step 2: Discovered race condition in token refresh"
  ],
  "files_checked": ["/absolute/path/to/file1.py", "/absolute/path/to/file2.py"],
  "issues_found": [
    {
      "severity": "critical",
      "description": "SQL injection in user query construction",
      "location": "auth.py:45",
      "impact": "Attackers can execute arbitrary SQL commands"
    }
  ]
}

Workflow Steps

Step 1: Initial Code Scan (Confidence: exploring)

Focus on:

  • Reading specified code files completely
  • Understanding structure, architecture, design patterns
  • Identifying obvious issues (bugs, security vulnerabilities, performance problems)
  • Noting code smells and anti-patterns
  • Looking for common vulnerability patterns

Read the full file on GitHub · 482 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. yesterday First seen · 482 lines · 14 tokens per session scan A 967e0b8f9eca

Subscribe to this mod's changes

codereview is a command published in the GitHub repository krmcbride/claude-plugins (3 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 3,230 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.