review

An AI code-review command that examines current changes, a branch difference, or a specific commit. A commit is a saved snapshot of code, and a branch is a separate line of development.

In plain words
What is it for?
Use it to review uncommitted work by default, compare a branch with another branch, inspect one commit, or request a review focused on a particular concern.
Why use it?
It helps find bugs, security problems, and style issues before code is merged or released.

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/pleaseai/claude-code-plugins/review
Clone the repo
git clone --depth 1 https://github.com/pleaseai/claude-code-plugins
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 733 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00047 $0.00733
Opus 5 $0.00023 $0.00367
Sonnet 5 $0.00009 $0.00147
Haiku 4.5 $0.00005 $0.00073

Measured yesterday against content hash 82aa6ad8ab12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

review scanned grade B with 2 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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://cubic.dev/install | bash

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://cubic.dev/install | bash
plugins/cubic/commands/review.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cubic AI Code Review

Run an AI-powered code review using Cubic CLI and apply fixes.

Workflow

Step 1: Determine review scope

Analyze $ARGUMENTS to determine the review mode:

User Intent Command
Review uncommitted changes (default) cubic review --json
Review branch diff against base cubic review --base <branch> --json
Review specific commit cubic review --commit <ref> --json
Review with custom focus cubic review --prompt "<instructions>" --json

If $ARGUMENTS is empty, default to reviewing uncommitted changes.

Step 1.5: Sanitize arguments

Before constructing any Bash command, validate that user-provided values (branch names, commit refs, prompt text) do not contain shell metacharacters (;, &&, ||, |, `, $(), ', newlines). Always use single quotes around user-provided values when interpolating into shell commands. Reject any input containing command separators, substitution patterns, or single quotes (which break single-quote escaping).

Step 2: Run Cubic review

Execute the appropriate command via Bash. Always include --json for structured output. Ensure all user-provided arguments are properly shell-quoted.

cubic review --json

If cubic is not installed, inform the user:

cubic CLI is not installed. Install it with:
  curl -fsSL https://cubic.dev/install | bash
  # or: npm install -g @cubic-dev-ai/cli

Step 3: Parse and analyze results

Parse the JSON output. Each issue contains:

  • priority: Severity level (P0 = critical, P1 = high, P2 = medium, P3 = low)
  • file: File path where the issue was found
  • line: Line number of the issue
  • title: Brief description of the issue
  • description: Detailed explanation

Step 4: Present findings

Summarize the review results grouped by priority:

=== Cubic Review Results ===

Found N issues (X critical, Y high, Z medium, W low)

[P0] file:line - title
  description

[P1] file:line - title
  description

...

Read the full file on GitHub · 99 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 · 99 lines · 47 tokens per session scan B 82aa6ad8ab12

Subscribe to this mod's changes

review is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 733 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.