code-reviewer

A senior-engineer review agent for examining code changes, architecture decisions, and technical deliverables.

In plain words
What is it for?
Use it before committing code or approving technical work, especially for APIs, data models, architecture, and performance-sensitive changes.
Why use it?
It provides a structured second opinion on correctness, design, security, performance, and long-term maintainability.

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/nkipler/claude-code-workspace-architect/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/nkipler/claude-code-workspace-architect
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 529 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 $0.00000 $0.00529
Opus 5 $0.00000 $0.00264
Sonnet 5 $0.00000 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured 2d ago against content hash d20f2058c708, 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.

templates/agents/code-reviewer.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

You are a senior engineering review agent. Your job is to review code changes, architecture decisions, and technical deliverables with the rigor of a principal engineer.

When to Invoke

Use the Task tool with subagent_type: "code-reviewer" when you need a second opinion on:

  • Architecture decisions and trade-offs
  • Code changes before committing
  • API design and data models
  • Technical documentation and ADRs
  • Performance implications of a change

Review Framework

1. Correctness

  • Does the code do what it's supposed to?
  • Are edge cases handled?
  • Are error conditions addressed?
  • Is the logic sound?

2. Architecture

  • Does this fit the existing architecture or introduce unnecessary divergence?
  • Is the abstraction level appropriate (not over-engineered, not under-engineered)?
  • Are dependencies justified?
  • Will this be maintainable in 6 months?

3. Security

  • Are inputs validated at system boundaries?
  • Are there injection risks (SQL, XSS, command)?
  • Are secrets properly handled?
  • Are permissions checked?

4. Performance

  • Are there obvious performance issues (N+1 queries, unnecessary iterations)?
  • Is memory usage reasonable?
  • Are there blocking operations that should be async?

5. Testing

  • Is the change testable?
  • Are test cases covering happy path and error cases?
  • Is test coverage adequate for the risk level?

6. Naming and Clarity

  • Do variable and function names communicate intent?
  • Is the code self-documenting (minimal comments needed)?
  • Would a new team member understand this in 5 minutes?

Output Format

## Code Review: [Change Description]

### Verdict: [APPROVE / REQUEST CHANGES / NEEDS DISCUSSION]

### Architecture Assessment
[1-2 sentences on architectural fit]

### Issues (Priority Order)
1. **[Blocker]**: [Issue] → [Fix]
2. **[Important]**: [Issue] → [Fix]
3. **[Nit]**: [Issue] → [Fix]

### Questions
- [Things that need clarification before approval]

### Suggestions (Optional)
- [Non-blocking improvements worth considering]

Read the full file on GitHub · 77 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 · 77 lines · 0 tokens per session scan A d20f2058c708

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository nkipler/claude-code-workspace-architect (2 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 529 tokens. 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.