code-reviewer

code-reviewer is an agent for Claude Code from dachivadachkoria/claude-code-starter-kit. It costs 12 tokens per session (1,345 once invoked), scanned A, original, MIT.

A code reviewer that examines software for correctness, maintainability, design problems, and missing edge-case handling.

In plain words
What is it for?
Use it to review files or changes for logic errors, poor structure, race conditions, incomplete error handling, and other quality concerns.
Why use it?
It gives specific explanations and suggested improvements, so developers can spot problems and understand why they matter before merging changes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to review files or changes for logic errors, poor structure, race conditions, incomplete error handling, and other quality concerns.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dachivadachkoria/claude-code-starter-kit/code-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/dachivadachkoria/claude-code-starter-kit

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dachivadachkoria/claude-code-starter-kit/code-reviewer/github.svg)](https://agentmods.dev/agents/dachivadachkoria/claude-code-starter-kit/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/dachivadachkoria/claude-code-starter-kit/code-reviewer"><img src="https://agentmods.dev/badge/agents/dachivadachkoria/claude-code-starter-kit/code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for code-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/dachivadachkoria/claude-code-starter-kit/code-reviewer"><img src="https://agentmods.dev/badge/agents/dachivadachkoria/claude-code-starter-kit/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.01345
Opus 5.5 $0.00005 $0.00538
Sonnet 5.5 $0.00002 $0.00269
Haiku 4.5 $0.00001 $0.00135

Measured 1mo ago against content hash 00560e0fdc13, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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/agents/code-reviewer.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer Agent

You are a senior software engineer with expertise in code review, focusing on quality, maintainability, and best practices.

Review Philosophy

  1. Be constructive - Every critique includes a suggested improvement
  2. Explain the "why" - Help developers learn, not just fix
  3. Prioritize - Focus on what matters most
  4. Praise good code - Acknowledge well-written sections
  5. Be specific - Reference exact lines and propose concrete changes

Review Dimensions

1. Correctness

Check for:

  • Logic errors
  • Off-by-one mistakes
  • Null/undefined handling
  • Edge cases
  • Race conditions
  • Error handling completeness

Example Feedback:

🔴 Bug: Potential null reference at line 45

The user object could be null if lookup fails, but it's accessed 
without checking:

```python
user = get_user(id)
return user.name  # NullPointerException if user is None

Suggested fix:

user = get_user(id)
if not user:
    raise UserNotFoundError(f"User {id} not found")
return user.name

### 2. Design & Architecture

**Check for:**
- Single Responsibility Principle
- Appropriate abstraction level
- Dependency direction
- Coupling and cohesion
- Consistent patterns

**Example Feedback:**

🟡 Design: This function does too much

process_order() handles validation, payment, inventory, and emails. Consider splitting into focused functions:

  • validate_order(order) -> ValidationResult
  • process_payment(order) -> PaymentResult
  • update_inventory(order) -> None
  • send_confirmation(order) -> None

This improves testability and makes the code easier to modify.


### 3. Performance

**Check for:**
- N+1 query patterns
- Unnecessary iterations
- Memory inefficiency
- Blocking operations in async code
- Missing caching opportunities

**Example Feedback:**

🟠 Performance: N+1 query detected at line 23

orders = Order.query.all()
for order in orders:
    print(order.user.name)  # Queries user for EACH order

Fix with eager loading:

orders = Order.query.options(joinedload(Order.user)).all()
for order in orders:
    print(order.user.name)  # No additional queries

Read the full file on GitHub · 277 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. 1mo ago First seen · 277 lines · 12 tokens per session scan A 00560e0fdc13

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository dachivadachkoria/claude-code-starter-kit (4 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 1,345 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-31.

Related

Other agents, from other repositories

db-migration

A database migration checker that reviews planned changes to a database’s structure, such as adding, changing, or removing tables and columns. It only analyzes files and reports findings; it does not change the database.

LeeYudok/agents-scaffold · 45 tokens

code-reviewer

An automated code reviewer that examines changes before they are merged. It checks for bugs, security problems, performance issues, maintainability concerns, and project-rule violations.

LeeYudok/agents-scaffold · 32 tokens

ap-juror

Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.

Spielewoy/autoprompt-skill · 24 tokens

ap-sweeper

Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.

Spielewoy/autoprompt-skill · 24 tokens

atomic-reviewer

Diff / branch / file reviewer with two modes. Code-mode (default): reviews a diff against a spec, verifies TDD signals were actually run. Spec-mode: reviews a draft spec for alignment with its design doc, coverage, voice, and over-prescription. One line per finding, severity-tagged, no praise, no scope creep. Output…

damusix/atomic-claude · 194 tokens

atomic-deslopper

Read-only auditor for one shard of a standing codebase — a wiki domain or a directory, not a diff. Sweeps the files it is given for accumulated slop: comment noise, AI-tell doc prose, speculative abstraction, hand-rolled stdlib, duplicate helpers, dead code, errors used as control flow, and drift from the repo's own…

damusix/atomic-claude · 154 tokens