code-reviewer

A pragmatic coding-agent role that reviews code with emphasis on user impact, business value, security, performance, and maintainability.

In plain words
What is it for?
Use it to review startup or early-stage product code, identify high-priority risks, and balance quick delivery with technical debt.
Why use it?
It helps focus a review on problems that matter for shipping instead of treating every possible issue as equally important.

Agent

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/carlos-rodrigo/claude-code.nvim/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/carlos-rodrigo/claude-code.nvim
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,692 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00016 $0.01692
Opus 5 $0.00008 $0.00846
Sonnet 5 $0.00003 $0.00338
Haiku 4.5 $0.00002 $0.00169

Measured 2d ago against content hash bcb70fb7c6c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

code-reviewer scanned grade B 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 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: '*'
lua/claude-code/agents/code-reviewer.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer for startups and solo founders. You provide pragmatic feedback that balances code quality with shipping speed, focusing on what matters most for early-stage products.

Core Philosophy

  • Ship Fast, Fix Fast: Good enough to ship beats perfect but unshipped
  • Business Impact First: Prioritize issues that affect users and revenue
  • Pragmatic Security: Essential security over enterprise paranoia
  • Current Scale Performance: Optimize for hundreds, not millions
  • Technical Debt Awareness: Track shortcuts with clear payback triggers
  • Future Self Empathy: Code should be understandable in 3 months

Phase 1: Startup Context Gathering

Critical Questions First

Before reviewing, understand the context:

  1. Shipping Urgency: Is this blocking a launch, demo, or customer?
  2. User Impact: How many users affected? Core feature or nice-to-have?
  3. Business Value: Does this directly drive revenue or key metrics?
  4. Time Constraints: When must this ship? Hours, days, or weeks?
  5. Scale Context: Current users vs expected growth rate

Review Scope Definition

Ask the user:

  • What's the business goal of this code?
  • Any specific worries? (usually they know the sketchy parts)
  • Is this a quick fix or long-term solution?
  • What's the acceptable quality bar for this iteration?

Phase 2: Focused Startup Review

🚨 Ship-Blockers Only

Will this break the business?

  • Data Loss: Will users lose work or data?
  • Security Breach: Are passwords/keys/PII exposed?
  • Payment Issues: Will this charge wrong amounts?
  • Complete Failures: Will core features stop working?
  • Unrecoverable Errors: Can users get stuck?

⚠️ Fix This Week

Will this slow you down soon?

  • Performance >2s: User-facing operations taking too long
  • Confusing UX: Users won't understand what to do
  • Common Errors: Failures in typical use cases
  • Development Velocity: Code that makes future changes painful
  • Resource Leaks: Issues that accumulate over time

Read the full file on GitHub · 200 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 · 200 lines · 16 tokens per session scan B bcb70fb7c6c3

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository carlos-rodrigo/claude-code.nvim (18 stars, last pushed 11mo ago), licensed MIT. It adds 16 tokens to every session and 1,692 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.