review-code

A read-only code review command that examines the changes in your working directory against a defined checklist.

In plain words
What is it for?
Use it to review a diff, assign issues severity levels, and receive file-and-line findings plus an approval recommendation.
Why use it?
It helps find correctness, performance, readability, and error-handling problems before changes are approved. It reports issues without modifying your files.

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/kastheco/claude-plugins/review-code
Clone the repo
git clone --depth 1 https://github.com/kastheco/claude-plugins
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 251 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 $0.00009 $0.00251
Opus 5 $0.00005 $0.00125
Sonnet 5 $0.00002 $0.00050
Haiku 4.5 $0.00001 $0.00025

Measured yesterday against content hash 1668a797575d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-code 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.

plugins/kas/commands/review-code.md · 44 lines

What it actually says

/kas:review-code - Code Quality Review

Run a ruthless code review channeling Linus Torvalds philosophy.

Workflow

1. Identify scope

git status
git diff --stat

If no changes, report "Nothing to review" and stop.

2. Read agent instructions

Read agents/code-reviewer.md (relative to plugin root) and apply the review philosophy, checklist, and output format defined there.

3. Execute review

Review the changes following the agent's:

  • Review philosophy (simplicity, correctness, performance, readability, error handling)
  • Severity levels (Critical 91-100, High 71-90, Medium 41-70, Low 1-40)
  • Review checklist
  • Output format

4. Return findings

Provide structured output with:

  • Overall assessment: APPROVED / NEEDS CHANGES / REJECTED
  • Issues by severity with file:line references
  • Positive observations

Rules

  • Read-only: Never edit files
  • Return structured findings, do not apply fixes
  • Address all Critical and High issues before approving
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 · 44 lines · 9 tokens per session scan A 1668a797575d

Subscribe to this mod's changes

review-code is a command published in the GitHub repository kastheco/claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 251 once invoked, about $0.0000 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.