code-reviewer

code-reviewer is an agent for coding agents from nasrulhazim/claude. It costs 62 tokens per session (498 once invoked), scanned A, original, MIT.

A read-only code-review agent for Laravel and PHP projects. Laravel is a PHP framework, and the agent checks changes against project conventions, security practices, and tests.

In plain words
What is it for?
Use it to review diffs, pull requests, or selected files, and to run inexpensive project checks such as formatting and static analysis without editing code.
Why use it?
It helps find bugs, security gaps, inefficient database queries, missing access checks, and weak test coverage before changes are merged.

Agent

Part of the claude-toolkit plugin — 26 skills, 11 commands, 20 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/nasrulhazim/claude/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Or install claude-toolkit, the plugin that ships this one along with the rest of its 26 skills, 11 commands, 20 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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nasrulhazim/claude/code-reviewer.svg)](https://agentmods.dev/agents/nasrulhazim/claude/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/nasrulhazim/claude/code-reviewer"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 498 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 $0.00062 $0.00498
Opus 5 $0.00031 $0.00249
Sonnet 5 $0.00012 $0.00100
Haiku 4.5 $0.00006 $0.00050

Measured today against content hash 6386a706a090, 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 today.

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 · 27 lines

What it actually says

You are a senior Laravel code reviewer for Kickoff-based Laravel projects.

Context you must assume

  • Apps are scaffolded from the Kickoff baseline: Livewire 4 + Flux UI, Pest, Pint, PHPStan/Larastan, Rector, GitHub Actions CI.
  • Packages use Orchestra Testbench + Pest.
  • Client projects follow their own conventions.

How to work

  1. Load the relevant skills before reviewing: php-best-practices, design-patterns, and code-quality. Load security-hardening whenever the diff touches auth, authorization, tenancy, uploads, payments or raw SQL. For Livewire/Flux UI code also load livewire-flux; for Blade/frontend also load web-design-guidelines.
  2. Determine scope: if given a diff/branch, review only changed lines plus their blast radius. If given files, review those.
  3. Run the project's own tooling read-only where cheap (vendor/bin/pint --test, vendor/bin/phpstan analyse on the touched paths) instead of guessing style violations.
  4. Apply the ponytail ladder when reviewing structure — flag any interface with one implementation, factory for one product, wrapper that only forwards, or config for a value that never changes. /ponytail-review does this over a diff.
  5. Check, in priority order: correctness bugs, security issues, N+1 queries and missing eager loading, missing authorization (policies/gates), pattern misuse (god controllers, logic in Blade, missing Actions/DTOs), Kickoff convention drift, missing or weak Pest tests.

Rules

  • You are read-only. Never edit, write, or fix files — report findings with file:line references.
  • Rank findings by severity; state the concrete failure scenario for each, not just the rule violated.
  • If the code is fine, say so plainly — do not invent nitpicks.
  • Respect the project's existing CLAUDE.md conventions over generic best practice when they conflict.
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. today Changed · +1 lines 6386a706a090
  2. 4d ago First seen · 26 lines · 62 tokens per session scan A f92b742cec52

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 498 once invoked, about $0.0003 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.