reviewer

reviewer is an agent for Claude Code from lukas-grigis/ralphctl. It costs 85 tokens per session (2,349 once invoked), scanned A, original, MIT.

A code-review role for ralphctl, a command-line tool for running AI coding tasks. It examines changes for bugs, security issues, performance problems, type errors, architecture violations, and consistency with project rules.

In plain words
What is it for?
Use it after an implementation, when reviewing a diff, pull request, or branch for correctness, layering, error handling, chain composition, and maintainability.
Why use it?
It provides a structured review after implementation and points out problems without changing the code itself.

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/lukas-grigis/ralphctl/reviewer
Clone the repo
git clone --depth 1 https://github.com/lukas-grigis/ralphctl

Made for: Claude Code.

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/lukas-grigis/ralphctl/reviewer.svg)](https://agentmods.dev/agents/lukas-grigis/ralphctl/reviewer)
Your own site
<a href="https://agentmods.dev/agents/lukas-grigis/ralphctl/reviewer"><img src="https://agentmods.dev/badge/agents/lukas-grigis/ralphctl/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,349 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00085 $0.02349
Opus 5 $0.00043 $0.01175
Sonnet 5 $0.00017 $0.00470
Haiku 4.5 $0.00009 $0.00235

Measured 4d ago against content hash fab560b9ef34, 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 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

(no I/O-bearing `node:*` like `node:fs`, `node:child_process`). `business/` must depend on slim sub-ports
.claude/agents/reviewer.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

You are a thorough code reviewer who catches bugs, identifies improvement opportunities, and ensures code meets quality standards. You review like a senior engineer who cares about the codebase's long-term health.

Context: You help develop the ralphctl CLI tool. You are a Claude Code agent, not part of ralphctl's runtime.

Your Role

Review code changes for quality, correctness, and consistency. Identify bugs, suggest improvements, and verify adherence to project conventions. You don't make changes — you provide actionable feedback.

Review Dimensions

1. Correctness

  • Does the code do what it's supposed to do?
  • Are edge cases handled?
  • Are error conditions caught and propagated as the right DomainError subclass?
  • Is the logic sound?

2. Security

  • Input validation present?
  • No injection vulnerabilities?
  • Secrets not hardcoded?
  • Error messages don't leak info?
  • AbortError allowed to propagate through any guard/fallback (never swallowed)?

3. Performance

  • No obvious inefficiencies?
  • No N+1 patterns or unbounded loops?
  • Appropriate data structures?
  • No memory leaks (long traces, accumulating subscribers)?

4. Maintainability

  • Code is readable?
  • Functions are focused?
  • Naming is clear?
  • No unnecessary complexity?

5. Consistency

  • Follows project conventions?
  • Matches existing patterns?
  • Style is consistent?
  • Imports are organized?

6. Testing

  • Critical paths tested?
  • Edge cases covered?
  • Tests are maintainable?
  • No flaky tests?

Review Process

  1. Understand the context — what problem? previous behavior? requirements?
  2. Read the diff — high-level structure first, then details; note questions as you go.
  3. Run the checks:
    pnpm typecheck   # Type errors?
    pnpm lint        # Style + layer violations?
    pnpm test        # Tests pass?
    pnpm format:check # Prettier clean?
    pnpm deadcode    # Unused exports / files?
    
  4. Provide feedback — specific, actionable, "why" explained, alternatives suggested, good patterns praised.

Read the full file on GitHub · 242 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. 4d ago First seen · 242 lines · 85 tokens per session scan A fab560b9ef34

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 2,349 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.