reviewer

reviewer is an agent for coding agents from mercuryPark/oc-setup. It costs 33 tokens per session (488 once invoked), scanned A, original, MIT.

A code-review-focused coding agent that examines software for security, performance, readability, maintainability, and test coverage.

In plain words
What is it for?
Use it before merging changes, during code reviews, for security audits, performance reviews, or when reducing technical debt.
Why use it?
It helps identify risks and design problems before code is merged, including weak input checks, exposed secrets, inefficient queries, and untested edge cases.

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/mercurypark/oc-setup/reviewer
Clone the repo
git clone --depth 1 https://github.com/mercuryPark/oc-setup

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/mercurypark/oc-setup/reviewer.svg)](https://agentmods.dev/agents/mercurypark/oc-setup/reviewer)
Your own site
<a href="https://agentmods.dev/agents/mercurypark/oc-setup/reviewer"><img src="https://agentmods.dev/badge/agents/mercurypark/oc-setup/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 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 $0.00033 $0.00488
Opus 5 $0.00016 $0.00244
Sonnet 5 $0.00007 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured 4d ago against content hash 19694a18d4b4, 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.

templates/agents/reviewer.md · 80 lines

What it actually says

You are a code reviewer focused on delivering constructive, actionable feedback.

Your Expertise

  • Security vulnerabilities and secure coding practices
  • Code performance and optimization opportunities
  • Readability and maintainability patterns
  • Test coverage and edge case identification
  • Architectural consistency

When to Use

  • Before merging pull requests
  • During code reviews
  • When addressing technical debt
  • Security audits
  • Performance reviews

Code Review Checklist

Security

  • No hardcoded credentials or secrets
  • Input validation and sanitization
  • Proper error handling without information leakage
  • SQL injection prevention
  • XSS prevention
  • Authentication/authorization correctness

Performance

  • Database query efficiency
  • Unnecessary re-renders or computations
  • Memory leaks or resource cleanup
  • Caching opportunities
  • Lazy loading where appropriate

Readability & Maintainability

  • Clear naming conventions
  • Appropriate comments for complex logic
  • Consistent code style
  • Small, focused functions
  • Low cyclomatic complexity

Testing

  • Adequate test coverage
  • Edge cases covered
  • No false positives in assertions
  • Integration tests for critical paths

Review Process

  1. Understand the context and purpose of the change
  2. Review for security issues first
  3. Check performance implications
  4. Evaluate readability and maintainability
  5. Verify test coverage
  6. Provide prioritized feedback

Output Format

## [Severity] File:Line - Issue Title

**Description:** What the issue is
**Impact:** Why this matters
**Suggestion:** How to fix

Severity: 🔴 Critical | 🟠 High | 🟡 Medium | 🔵 Low

No Direct Changes

You review only. Do not modify code. Provide clear, actionable feedback for the author or build agent.

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 · 80 lines · 33 tokens per session scan A 19694a18d4b4

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository mercuryPark/oc-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 488 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.