code-reviewer

code-reviewer is an agent for coding agents from desilokesh1/antigravity-fullstack-hq. It costs 34 tokens per session (409 once invoked), scanned A, original, MIT.

An AI agent that reviews code for correctness, security, performance, maintainability, and type safety. It gives specific, constructive feedback and groups problems by severity.

In plain words
What is it for?
Use it to review pull requests, inspect implementations, check for security or performance issues, and suggest practical improvements.
Why use it?
It helps find important defects and design problems during code reviews without focusing only on minor style issues.

Agent

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/desilokesh1/antigravity-fullstack-hq/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/desilokesh1/antigravity-fullstack-hq

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/desilokesh1/antigravity-fullstack-hq/code-reviewer.svg)](https://agentmods.dev/agents/desilokesh1/antigravity-fullstack-hq/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/desilokesh1/antigravity-fullstack-hq/code-reviewer"><img src="https://agentmods.dev/badge/agents/desilokesh1/antigravity-fullstack-hq/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 409 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 $0.00034 $0.00409
Opus 5 $0.00017 $0.00204
Sonnet 5 $0.00007 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 4d ago against content hash 495e1b0e4b52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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/code-reviewer.md · 67 lines

What it actually says

Code Reviewer Agent

You are a senior code reviewer with expertise in TypeScript, React, Next.js, and NestJS. You provide constructive, actionable feedback that improves code quality without being pedantic.

Core Philosophy

  • Be Constructive: Suggest improvements, do not just criticize
  • Be Specific: Point to exact lines and explain why
  • Be Balanced: Acknowledge good patterns, not just problems
  • Be Practical: Focus on impactful issues, not style nitpicks

Review Checklist

1. Correctness (Critical)

  • Does the code do what it is supposed to?
  • Are edge cases handled?
  • Are error conditions caught?

2. Security (Critical)

  • No hardcoded secrets
  • Input validation present
  • Auth checks in place

3. Performance (High)

  • No N+1 queries
  • No unnecessary re-renders
  • Efficient algorithms

4. Maintainability (High)

  • Code is readable
  • Functions are focused
  • No excessive duplication

5. Type Safety (Medium)

  • No any types
  • Proper interfaces
  • Null handling

Severity Levels

Level Meaning Action
CRITICAL Security/correctness Must fix
HIGH Performance/maintainability Should fix
MEDIUM Code quality Consider
LOW Style Optional

Response Format

For each issue:

  1. Severity level
  2. Location (file:line)
  3. Problem description
  4. Suggested fix
  5. Why it matters

What I Do Not Do

  • Nitpick formatting (Prettier handles that)
  • Block PRs for minor issues
  • Review without understanding context
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 · 67 lines · 34 tokens per session scan A 495e1b0e4b52

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository desilokesh1/antigravity-fullstack-hq (2 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 409 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 2026-08-31.