review

review is a command for coding agents from Joncik91/ucai. It costs 7 tokens per session (909 once invoked), scanned A, original, MIT.

A code-review command that uses multiple independent checks to examine code changes. Code review means looking for defects, risks, and maintainability problems before changes are accepted.

In plain words
What is it for?
Use it to review local changes or a chosen set of files, while checking project lessons and applying relevant review guidance.
Why use it?
It helps catch issues in unstaged changes or a specified review scope that one pass might miss.

Command

Part of the ucai plugin — 8 skills, 10 commands, 8 agents, 8 hooks shipped together

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/joncik91/ucai/review
Clone the repo
git clone --depth 1 https://github.com/Joncik91/ucai

Or install ucai, the plugin that ships this one along with the rest of its 8 skills, 10 commands, 8 agents, 8 hooks.

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/joncik91/ucai/review.svg)](https://agentmods.dev/commands/joncik91/ucai/review)
Your own site
<a href="https://agentmods.dev/commands/joncik91/ucai/review"><img src="https://agentmods.dev/badge/commands/joncik91/ucai/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 909 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 $0.00007 $0.00909
Opus 5 $0.00003 $0.00454
Sonnet 5 $0.00001 $0.00182
Haiku 4.5 $0.00001 $0.00091

Measured 4d ago against content hash f2d6b9d40f58, 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 4d 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.

commands/review.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

You are performing a thorough code review using parallel agents for independent analysis.

Context

  • Review scope: $ARGUMENTS (default: unstaged changes via git diff)
  • Current git status: !git status
  • Current git diff: !git diff HEAD

Skill Loading — MANDATORY

Before starting Phase 2, you MUST load the ucai:code-reviewer skill — this is a code review workflow.

  1. Load: Skill(ucai:code-reviewer)
  2. Also load the domain skill matching the code being reviewed: Skill(ucai:backend), Skill(ucai:frontend), etc.
  3. Apply the skill's guidance when evaluating code quality and conventions

You MUST load at least one skill before proceeding. State which skill(s) you loaded and why.


Phase 1: Scope

Goal: Determine what to review.

Lessons loading: If tasks/lessons.md exists, read it and note any patterns relevant to the code being reviewed. Feed known patterns (common mistakes, project-specific gotchas, past corrections) as context to Phase 2 reviewer agents so they can watch for recurrence. If the file doesn't exist, skip silently.

Actions:

  1. Create todo list
  2. If $ARGUMENTS specifies files or a PR, use that scope
  3. If no arguments, review unstaged changes from git diff
  4. If no changes found, tell the user and stop
  5. Find any CLAUDE.md files in the project for guideline reference
  6. Check for .claude/project.md and .claude/requirements.md. If found, read them — pass project conventions and non-functional requirements (security, performance targets) as context to Phase 2 reviewer agents so they can validate against project-level specs.
  7. If tasks/lessons.md exists, load it and extract patterns relevant to the review scope — include these in Phase 2 agent prompts

Phase 2: Parallel Review

Goal: Get independent perspectives on the code.

MANDATORY: You MUST use the Task tool to launch 3 reviewer agents in parallel. Do NOT skip agents and review the code yourself — independent parallel review catches issues that single-pass review misses.

Read the full file on GitHub · 93 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. 4d ago First seen · 93 lines · 7 tokens per session scan A f2d6b9d40f58

Subscribe to this mod's changes

review is a command published in the GitHub repository Joncik91/ucai (29 stars, last pushed 8d ago), licensed MIT. It adds 7 tokens to every session and 909 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.