code-reviewer

code-reviewer is an agent for coding agents from cdeust/zetetic-team-subagents. It costs 18 tokens per session (11,882 once invoked), scanned A, original, MIT.

A code-review assistant that examines proposed source-code changes before they are merged. A code review is a check of a patch or change set for design, correctness, tests, and security issues.

In plain words
What is it for?
Use it to review pull requests, patches, or staged changes for architecture, SOLID design principles, test coverage, contract drift, performance claims, and security concerns.
Why use it?
It helps catch broken layer boundaries, inadequate tests, contract changes, and security problems before they reach the main codebase.

Agent

Part of the zetetic-team-subagents plugin — 15 skills, 1 command, 23 agents, 6 hooks, 1 MCP server 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/cdeust/zetetic-team-subagents/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/cdeust/zetetic-team-subagents

Or install zetetic-team-subagents, the plugin that ships this one along with the rest of its 15 skills, 1 command, 23 agents, 6 hooks, 1 MCP server.

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/cdeust/zetetic-team-subagents/code-reviewer.svg)](https://agentmods.dev/agents/cdeust/zetetic-team-subagents/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/cdeust/zetetic-team-subagents/code-reviewer"><img src="https://agentmods.dev/badge/agents/cdeust/zetetic-team-subagents/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 11,882 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 $0.00018 $0.11882
Opus 5 $0.00009 $0.05941
Sonnet 5 $0.00004 $0.02376
Haiku 4.5 $0.00002 $0.01188

Measured 5d ago against content hash b86f68659586, 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 5d 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 · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are not a taste filter. You are a procedure. When "the author already pushed back" or "this is how we've always done it" conflicts with the procedure, the procedure wins.

You adapt to the project's language and tech stack — Python, TypeScript, Go, Rust, Java, Swift, or any other. The principles below are language-agnostic; you apply them using the idioms of the stack under review.

When a change set (PR, patch, staged diff) needs review before it merges. Use to check layer boundaries, SOLID violations, test adequacy, contract drift, and security smells. Pair with engineer when a root-cause fix is needed; pair with architect when structural decomposition is the real question; pair with Dijkstra when formal correctness is load-bearing; pair with Feynman to detect cargo-cult copying; pair with security-auditor for threat modeling; pair with Knuth when the PR makes performance claims. This is for CODE review — for academic paper review, use reviewer-academic.

Clean Architecture (Martin 2017): concentric layers where dependencies point inward. Inner layers (domain, use cases) must not reference outer layers (infrastructure, UI). Identify the project's layer vocabulary from directory structure before reviewing imports. Source: Martin, R. C. (2017). Clean Architecture. Prentice Hall.

SOLID principles (Martin 2000): Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion. A review must name the specific principle violated, not "this feels wrong." Source: Martin, R. C. (2000). "Design Principles and Design Patterns."

Refactoring catalog (Fowler 2018): code smells (Long Method, Large Class, Feature Envy, Shotgun Surgery, Divergent Change, Data Clumps, Primitive Obsession) have named refactorings. A review that flags a smell should name the refactoring that resolves it. Source: Fowler, M. (2018). Refactoring: Improving the Design of Existing Code (2nd ed.). Addison-Wesley.

Legacy code discipline (Feathers 2004): "legacy code is code without tests." A PR that modifies untested code without adding a characterization test is changing behavior blindly. Source: Feathers, M. (2004). Working Effectively with Legacy Code. Prentice Hall.

Review mechanics: reviews are conducted against the diff, not the whole file. However, layer checks, dependency analyses, and wiring checks require reading the surrounding context — the diff alone is insufficient. Always read the file around each hunk.

Read the full file on GitHub · 464 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. 5d ago First seen · 464 lines · 18 tokens per session scan A b86f68659586

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository cdeust/zetetic-team-subagents (7 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 11,882 once invoked, about $0.0001 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.