review

review is a command for Claude Code, Cursor from redhat-community-ai-tools/UnifAI. It costs 0 tokens per session (260 once invoked), scanned A, original, Apache-2.0.

A code-review command with basic and deep modes, optionally limited to chosen files or folders. Code review is a check of changes for bugs, design problems, and risks.

In plain words
What is it for?
Use it after developing a feature to inspect the branch changes, compare them with a design or architecture document, and document issues by area and severity.
Why use it?
It organizes review findings and records them in a branch-specific Markdown report, while deep reviews can also use or create a design reference.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

Good fit Use it after developing a feature to inspect the branch changes, compare them with a design or architecture document, and document issues by area and severity.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/redhat-community-ai-tools/unifai/review
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.

Clone the repo
git clone --depth 1 https://github.com/redhat-community-ai-tools/UnifAI

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/review/github.svg)](https://agentmods.dev/commands/redhat-community-ai-tools/unifai/review)
Your own site
<a href="https://agentmods.dev/commands/redhat-community-ai-tools/unifai/review"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/redhat-community-ai-tools/unifai/review"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/unifai/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00260
Opus 5 $0.00000 $0.00130
Sonnet 5 $0.00000 $0.00052
Haiku 4.5 $0.00000 $0.00026

Measured 11d ago against content hash 97748d5e5621, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 11d 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.

.cursor/commands/review.md · 13 lines

What it actually says

This command might include optional parameters basic / deep - this is the type of review to invoke if no parameter is given for that option the default should be basic files/folders - if file or folder specification is given only review them.

following my developing a new feature please follow these steps:

  1. go over the code, and get all the changes.
  2. (only if deep review) prepare a design you can use as a reference, in addition where the folder containing parts of the new feature includes an architecture.md file use it as reference as well.
  3. review the code added in this branch and gather all your comments in a file named <branch_name>_<review_type>_review.md (where branch name is the actual branch name you checked). pay close attention to the design and make sure it's not being broken in any way the review file should be built like this:
  4. list of issues found split by areas and severity (area first)
  5. at the top a short overview of the review and the purpose of the feature as you understood it
  6. if a design is available add it to the file (if you created the design by running deep review add it as is if the design is part of the added files to the branch just specify its location)
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. 11d ago First seen · 13 lines · 0 tokens per session scan A 97748d5e5621

Subscribe to this mod's changes

review is a command published in the GitHub repository redhat-community-ai-tools/UnifAI (44 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 260 tokens. 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.