review

A shell-script code-review command that reports security, quality, and cross-platform issues with suggested fixes and an overall verdict.

In plain words
What is it for?
Use it to review shell-script changes for unsafe commands, quoting and error-handling problems, portability across macOS and Linux, and compatibility with PowerShell or WSL.
Why use it?
It gives a consistent review before merging changes or after substantial script edits.

Command for Claude Code

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/mylee04/code-notify/review
Clone the repo
git clone --depth 1 https://github.com/mylee04/code-notify

Made for: Claude Code.

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 292 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 $0.00005 $0.00292
Opus 5 $0.00003 $0.00146
Sonnet 5 $0.00001 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 2d ago against content hash 47593144f15f, 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.

.claude/commands/review.md · 70 lines

What it actually says

Code Review

What This Command Does

  1. Analyzes code for security issues
  2. Checks shell scripting best practices
  3. Verifies cross-platform compatibility
  4. Provides improvement suggestions

When to Use

  • Before merging PRs
  • After significant changes
  • When adding new features

Process

1. Invoke Code Reviewer Agent

The code-reviewer agent will analyze:

  • Security vulnerabilities
  • Shell best practices
  • Cross-platform compatibility
  • Code quality

2. Review Areas

Security Checklist
  • No hardcoded credentials
  • Input sanitization
  • No command injection risks
  • Safe file handling
Best Practices
  • Variables quoted
  • Functions use local
  • Error handling present
  • Commands existence checked
Cross-Platform
  • Works on macOS
  • Works on Linux
  • PowerShell equivalent correct
  • WSL compatible

3. Output

Review generates a report with:

  • Issues found (by severity)
  • Specific line numbers
  • Suggested fixes
  • Overall verdict (APPROVE/NEEDS CHANGES/BLOCK)

Usage

Review the changes in lib/code-notify/core/notifier.sh

The code-reviewer agent will be invoked automatically.

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 · 70 lines · 5 tokens per session scan A 47593144f15f

Subscribe to this mod's changes

review is a command published in the GitHub repository mylee04/code-notify (288 stars, last pushed 4d ago), licensed MIT. It adds 5 tokens to every session and 292 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 2026-08-30.