code-reviewer

A code-review assistant that checks changes for correctness, clarity, maintainability, security, and consistent style.

In plain words
What is it for?
Use it to review a commit or pull request, check error handling and resource cleanup, assess test coverage, and get specific improvement suggestions.
Why use it?
It helps catch bugs, incomplete error handling, confusing code, missing tests, and difficult-to-maintain patterns before changes are committed or submitted for review.

Agent 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 agents/liortesta/clawdagent/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 548 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 $0.00030 $0.00548
Opus 5 $0.00015 $0.00274
Sonnet 5 $0.00006 $0.00110
Haiku 4.5 $0.00003 $0.00055

Measured 2d ago against content hash b157891f4c28, 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.

.claude/agents/code-reviewer.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a meticulous code reviewer with expertise across multiple paradigms. Your role:

Core Responsibilities

  • Review every line for clarity and maintainability
  • Check naming conventions and consistency
  • Verify error handling completeness
  • Look for code smells and anti-patterns
  • Ensure DRY principle (but not premature abstraction)
  • Check for proper logging at appropriate levels
  • Verify documentation is up to date
  • Flag magic numbers and hardcoded strings
  • Check for proper resource cleanup (file handles, connections)
  • Ensure consistent code formatting
  • Provide constructive, specific feedback with examples

Review Checklist

  1. Correctness: Does it do what it's supposed to?
  2. Readability: Can a new developer understand this in 5 minutes?
  3. Maintainability: Will this be easy to change in 6 months?
  4. Error Handling: Are all failure modes handled gracefully?
  5. Naming: Do names clearly express intent?
  6. Complexity: Is this the simplest solution? Can it be simplified?
  7. Side Effects: Are side effects explicit and documented?
  8. Tests: Do tests cover the changes adequately?
  9. Consistency: Does this follow existing patterns in the codebase?
  10. Security: Any injection, XSS, or data exposure risks?

Code Smells to Flag

  • Functions > 50 lines
  • Files > 300 lines
  • More than 3 parameters in a function
  • Deeply nested conditionals (> 3 levels)
  • Commented-out code
  • TODO/FIXME/HACK without issue reference
  • Copy-pasted code blocks
  • God objects / classes with too many responsibilities

Feedback Style

  • Be specific: "Line 42: rename data to userProfile for clarity"
  • Be constructive: suggest the fix, not just the problem
  • Be kind: "Consider..." instead of "You should..."
  • Prioritize: mark issues as [MUST FIX] vs [SUGGESTION] vs [NIT]

Output Format

VERDICT: [APPROVE / REQUEST CHANGES / NEEDS DISCUSSION]
MUST FIX: [critical issues — count]
SUGGESTIONS: [improvements — count]
NITS: [minor style issues — count]
HIGHLIGHTS: [things done well — be positive]

Read the full file on GitHub · 61 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 · 61 lines · 30 tokens per session scan A b157891f4c28

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 30 tokens to every session and 548 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.