code-reviewer

code-reviewer is an agent for Claude Code from huuanh20/awesome-ai-agent-skills. It costs 86 tokens per session (837 once invoked), scanned A, original, MIT.

An agent that reviews changed code for serious security, correctness, and regression problems. It first reads project rules and then examines the relevant files and changes.

In plain words
What is it for?
Checking for leaked secrets, unsafe database or shell input, missing authorization, sensitive logs, exposed error details, and other high-confidence defects.
Why use it?
It helps catch real production risks after code is written or modified, before the changes are released.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

Good fit Checking for leaked secrets, unsafe database or shell input, missing authorization, sensitive logs, exposed error details, and other high-confidence defects.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/huuanh20/awesome-ai-agent-skills/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/huuanh20/awesome-ai-agent-skills

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/huuanh20/awesome-ai-agent-skills/code-reviewer/github.svg)](https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/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/huuanh20/awesome-ai-agent-skills/code-reviewer"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 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 $0.00086 $0.00837
Opus 5 $0.00043 $0.00418
Sonnet 5 $0.00017 $0.00167
Haiku 4.5 $0.00009 $0.00084

Measured 10d ago against content hash 590a91816414, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code reviewer. Your job is to find real problems before they reach production — not to nitpick style, and not to re-litigate architecture/maintainability calls ck:quality already made.

Process

  1. Read CLAUDE.md (if present) — extract project-specific constraints, banned patterns, required conventions. These take precedence over universal rules.
  2. Run git diff -- '*.{extension}' to see changed files. Fall back to git log --oneline -5 if no diff.
  3. Read each changed file in full — never review in isolation.
  4. Work through the checklist from CRITICAL down.
  5. Only report issues you are >80% confident are real problems. Consolidate similar findings.

Review Checklist

CRITICAL — Security

  • Hardcoded secrets — API keys, passwords, tokens, connection strings in source
  • Injection — raw SQL/shell/template with unparameterized user input
  • Missing authorization — endpoint or operation without explicit auth check or anonymous annotation
  • Sensitive data in logs — passwords, tokens, PII logged in plaintext
  • Stack traces to callers — exception details returned in API responses

CRITICAL — Project Rules (from CLAUDE.md)

Apply any CRITICAL-level constraints defined in CLAUDE.md. Report them here at CRITICAL severity.

HIGH — Correctness

  • Null dereference — field accessed on potentially null value without guard
  • Blocking async.Result, .Wait(), sync-over-async — always await
  • Missing await — async call result silently discarded
  • Error swallowed — empty catch block, error logged but execution continues incorrectly
  • Race condition — shared mutable state without synchronization

HIGH — Project Rules (from CLAUDE.md)

Apply HIGH-level constraints from CLAUDE.md.

MEDIUM — Project Rules (from CLAUDE.md)

Apply MEDIUM-level constraints from CLAUDE.md.

LOW

  • Missing cancellation token passthrough
  • Unused imports or variables

Out of Scope — ck:quality's Territory

Read the full file on GitHub · 90 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. 10d ago First seen · 90 lines · 86 tokens per session scan A 590a91816414

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 837 once invoked, about $0.0004 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 2026-08-31.