ai-engineer-review

ai-engineer-review is a command for Claude Code from Benkapner/claude-code-basecamp. It costs 38 tokens per session (1,419 once invoked), scanned A, original, MIT.

A project review from the viewpoint of an experienced AI engineer, covering architecture, code quality, and the setup of agent skills, commands, and hooks.

In plain words
What is it for?
Use it to assess a project’s design, source code, tests, recent changes, and agent configuration, then receive specific suggestions for improvement.
Why use it?
It helps reveal structural problems, unfinished work, duplication, missing pieces, and setup issues that are easy to overlook when working on the project yourself.

Command 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 commands/benkapner/claude-code-basecamp/ai-engineer-review
Clone the repo
git clone --depth 1 https://github.com/Benkapner/claude-code-basecamp

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 ai-engineer-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/benkapner/claude-code-basecamp/ai-engineer-review.svg)](https://agentmods.dev/commands/benkapner/claude-code-basecamp/ai-engineer-review)
Your own site
<a href="https://agentmods.dev/commands/benkapner/claude-code-basecamp/ai-engineer-review"><img src="https://agentmods.dev/badge/commands/benkapner/claude-code-basecamp/ai-engineer-review.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 1,419 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 $0.01419
Opus 5 $0.00019 $0.00709
Sonnet 5 $0.00008 $0.00284
Haiku 4.5 $0.00004 $0.00142

Measured 5d ago against content hash fcfba161743d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-engineer-review 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.

.claude/commands/ai-engineer-review.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Engineer Review

Act as a principal AI engineer with 15+ years of experience reviewing this project. Be honest, specific, and critical — the goal is to find real problems, not to be encouraging or mean.

Instructions

Step 1: Understand the Project

Read the project's key files to understand what it does and how it's built:

# What is this project?
cat README.md 2>/dev/null | head -50
cat CLAUDE.md 2>/dev/null | head -50

# Structure
find . -maxdepth 2 -type f -name "*.py" -o -name "*.md" -o -name "*.yaml" | head -40

# Recent activity
git log --oneline -15
git diff --stat HEAD~5..HEAD 2>/dev/null

# Tests
ls tests/ 2>/dev/null

Step 2: Review Architecture

Assess the project's architecture and design decisions:

  • Is the structure logical? Are files in the right places? Are responsibilities clear?
  • Is it modular? Can you change one part without breaking others?
  • Is it over-engineered or under-engineered? Too many abstractions? Not enough?
  • Are there dead ends? Features started but not finished, orphaned files, unused code?
  • Data flow — is it clear how data moves through the system?

Step 3: Review Code Quality

For the main source files, check:

  • Duplication — same logic in multiple places
  • Complexity — functions doing too many things, deep nesting, long files
  • Error handling — swallowed errors, bare excepts, missing validation
  • Naming — unclear variable/function names, inconsistent conventions
  • Testing — coverage gaps, untested critical paths, brittle tests
  • Security — hardcoded secrets, injection risks, PII handling
  • Separation of concerns — each file/module has one clear responsibility with a well-defined interface
  • Coupling — can units be understood and tested independently? Can you change internals without breaking consumers?
  • SOLID principles — proper abstractions, dependency direction, interface segregation

Step 4: Review AI Workspace Setup (if applicable)

Read the full file on GitHub · 151 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 · 151 lines · 38 tokens per session scan A fcfba161743d

Subscribe to this mod's changes

ai-engineer-review is a command published in the GitHub repository Benkapner/claude-code-basecamp (16 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 1,419 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.