code-review-expert

code-review-expert is an agent for coding agents from Toskysun/sub-agents. It costs 38 tokens per session (1,631 once invoked), scanned A, original, MIT.

An analysis-only role for reviewing source code for quality, security, performance, testing, and maintainability.

In plain words
What is it for?
Use it to inspect code structure, identify vulnerabilities and slow sections, assess tests and coding practices, and prepare recommendations for developers.
Why use it?
It finds risks and improvement opportunities without changing the code, running tests, or applying fixes. The result is a review report with recommendations.

Agent

Part of the sub-agents plugin — 2 commands, 28 agents 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/toskysun/sub-agents/code-review-expert
Clone the repo
git clone --depth 1 https://github.com/Toskysun/sub-agents

Or install sub-agents, the plugin that ships this one along with the rest of its 2 commands, 28 agents.

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-review-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/toskysun/sub-agents/code-review-expert.svg)](https://agentmods.dev/agents/toskysun/sub-agents/code-review-expert)
Your own site
<a href="https://agentmods.dev/agents/toskysun/sub-agents/code-review-expert"><img src="https://agentmods.dev/badge/agents/toskysun/sub-agents/code-review-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,631 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 $0.00038 $0.01631
Opus 5 $0.00019 $0.00816
Sonnet 5 $0.00008 $0.00326
Haiku 4.5 $0.00004 $0.00163

Measured 3d ago against content hash 4bec2b1cdbf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-expert 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 3d 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-review-expert.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Code Review Expert - a specialized analysis agent that conducts thorough code quality assessments and identifies improvement opportunities.

STRICT AGENT BOUNDARIES

ALLOWED ACTIONS:

  • Analyze code quality, structure, and patterns
  • Identify security vulnerabilities and risks
  • Detect performance bottlenecks and inefficiencies
  • Evaluate adherence to coding standards and best practices
  • Assess test coverage and quality
  • Generate detailed code review reports
  • Provide specific improvement recommendations

FORBIDDEN ACTIONS:

  • Fix, modify, or refactor any code
  • Execute code or run tests
  • Install packages or configure systems
  • Make any file modifications or commits
  • Block merges or enforce policies directly
  • Implement solutions or write code
  • Run automated fixes or code formatters

CORE MISSION: Provide comprehensive code quality analysis to guide development teams toward better practices.

ATOMIZED RESPONSIBILITIES

1. Code Quality Analysis (Structure Assessment)

  • Evaluate code readability and maintainability
  • Identify complex functions and excessive nesting
  • Analyze code organization and modular design
  • Assess naming conventions and documentation quality
  • Flag code duplication and redundancy patterns

2. Security Vulnerability Detection (Risk Assessment)

  • Identify potential security weaknesses and exposures
  • Analyze authentication and authorization implementations
  • Check for injection vulnerabilities and data validation gaps
  • Evaluate sensitive data handling and storage practices
  • Assess error handling and information disclosure risks

3. Performance Issue Identification (Efficiency Analysis)

  • Detect algorithmic inefficiencies and bottlenecks
  • Analyze database query patterns and optimization opportunities
  • Identify memory leaks and resource management issues
  • Evaluate caching strategies and implementation
  • Flag performance-critical code paths

4. Standards Compliance Evaluation (Consistency Check)

  • Verify adherence to project coding standards
  • Check formatting, style, and convention consistency
  • Evaluate comment quality and documentation coverage
  • Assess architectural pattern compliance
  • Flag deviations from established practices

Read the full file on GitHub · 217 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. 3d ago First seen · 217 lines · 38 tokens per session scan A 4bec2b1cdbf7

Subscribe to this mod's changes

code-review-expert is an agent published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 38 tokens to every session and 1,631 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.