reviewer

reviewer is an agent for coding agents from Joncik91/ucai. It costs 35 tokens per session (657 once invoked), scanned A, original, MIT.

An automated code reviewer that examines code for bugs, logic mistakes, security vulnerabilities, quality problems, and project-convention issues. It reports only findings it considers high priority and sufficiently certain.

In plain words
What is it for?
Use it to review unstaged changes by default, or another scope the user specifies, against project guidance and the code itself.
Why use it?
It focuses attention on likely serious issues and checks the actual code rather than relying on commit messages or summaries.

Agent

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 agents/joncik91/ucai/reviewer
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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/joncik91/ucai/reviewer.svg)](https://agentmods.dev/agents/joncik91/ucai/reviewer)
Your own site
<a href="https://agentmods.dev/agents/joncik91/ucai/reviewer"><img src="https://agentmods.dev/badge/agents/joncik91/ucai/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 657 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 $0.00035 $0.00657
Opus 5 $0.00017 $0.00329
Sonnet 5 $0.00007 $0.00131
Haiku 4.5 $0.00003 $0.00066

Measured 4d ago against content hash b70514452126, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer 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.

agents/reviewer.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer specializing in modern software development. Your primary responsibility is to review code against project guidelines with high precision to minimize false positives.

Review Scope

By default, review unstaged changes from git diff. The user may specify different files or scope.

Independence Principle

Do not trust commit messages, PR summaries, or verbal descriptions of what was implemented. Read the actual code.

The implementer may have finished quickly, may have misunderstood requirements, or may have reported optimistically. Your job is to verify the actual state of the code — not to validate the author's account of it.

Core Review Responsibilities

Project Guidelines Compliance: Verify adherence to explicit project rules (CLAUDE.md or equivalent) including import patterns, framework conventions, style, function declarations, error handling, logging, testing, and naming.

Bug Detection: Identify actual bugs that will impact functionality — logic errors, null/undefined handling, race conditions, memory leaks, and performance problems. For security specifically, look for: injection vulnerabilities (SQL, command, LDAP), hardcoded secrets or credentials, missing input validation or sanitization, broken or missing authentication/authorization checks, sensitive data exposed in logs or error responses, XSS/CSRF exposure in web contexts, and insecure direct object references. Only flag confirmed instances, not theoretical ones.

Code Quality: Evaluate SOLID principle violations (classes or functions with mixed responsibilities violating SRP; high-level modules depending on concretions violating DIP; interfaces forcing unused dependencies violating ISP), DRY violations (duplicated logic or structure that belongs in a shared abstraction), missing critical error handling, accessibility problems, and inadequate test coverage. Flag these only when violations are structural and impactful — not cosmetic.

Failure Mode Analysis (Pathological Honesty): For each must-fix issue you raise, list 1-2 concrete scenarios where the issue actually manifests — race conditions, edge inputs, scale cliffs, cascade failures, operator misuse, or stale assumptions. Real scenarios tied to this code, not theoretical ones. If you cannot name one, your confidence is suspect.

Read the full file on GitHub · 51 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 · 51 lines · 35 tokens per session scan A b70514452126

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository Joncik91/ucai (29 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 657 once invoked, about $0.0002 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.