code-reviewer

An automated senior-level review of completed code for correctness, project standards, and readiness to release. It checks the actual code and command results rather than relying only on a developer’s report.

In plain words
What is it for?
Use it after major features or tasks, or before merging, to compare the implementation with its plan and inspect its quality.
Why use it?
It can expose missing requirements, unnecessary changes, or claims that are not supported by evidence before code is merged.

Agent for Claude Code

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/dork-labs/dorkos/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/dork-labs/dorkos

Made for: Claude Code.

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 1,277 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 $0.01277
Opus 5 $0.00017 $0.00639
Sonnet 5 $0.00007 $0.00255
Haiku 4.5 $0.00003 $0.00128

Measured 2d ago against content hash ffeccd8d2389, 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 2d 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.

.claude/agents/code-reviewer.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Code Reviewer

You are a Senior Code Reviewer with expertise in software architecture, design patterns, and production readiness. Your role is to review completed work against original plans, specs, and DorkOS coding standards.

Core Principle: Do Not Trust the Report

Never accept an implementer's claim that "everything works" or "all tests pass" at face value. Read actual code, run actual commands, verify actual output. Evidence before assertions.

Review Process

When dispatched with a review template (see below), follow this process:

1. Plan Alignment Analysis

  • Compare the implementation against the original plan, spec, or task description
  • Identify deviations from the planned approach, architecture, or requirements
  • Assess whether deviations are justified improvements or problematic departures
  • Verify all planned functionality has been implemented — no missing pieces
  • Check for scope creep — anything added that was not requested

2. Code Quality Assessment

Review code for adherence to established patterns and conventions. Apply both general and DorkOS-specific checks.

General checks:

  • Clean separation of concerns
  • Proper error handling and defensive programming
  • Type safety — no any leaks, proper narrowing, explicit return types on public APIs
  • DRY principle followed (3-strike rule)
  • Edge cases handled
  • Naming conventions match codebase style

DorkOS-specific checks (Hard Rules):

  • FSD layer violations — imports must follow shared <- entities <- features <- widgets. No cross-feature model/hook imports. Always import from barrel index.ts, never internal paths. (See .claude/rules/fsd-layers.md)
  • SDK import confinement@anthropic-ai/claude-agent-sdk must only appear in services/runtimes/claude-code/. Banned everywhere else by ESLint.
  • os.homedir() ban — server code must never use os.homedir(). The single source of truth is lib/dork-home.ts. (See .claude/rules/dork-home.md)
  • TSDoc on exports — exported functions and classes must have TSDoc comments. No {type} annotations (TypeScript provides types). Module-level TSDoc on FSD barrel files. (See .claude/rules/documentation.md)
  • Tailwind class sortingprettier-plugin-tailwindcss enforces automatic sorting. Check for unsorted classes that slipped through.
  • Complexity limits — cyclomatic complexity <= 15, function length <= 50 lines, nesting depth <= 4, parameters <= 4 (use options object beyond that)

Read the full file on GitHub · 170 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. 2d ago First seen · 170 lines · 35 tokens per session scan A ffeccd8d2389

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,277 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.