agentmods.dev

code-reviewer

code-reviewer is an agent for Claude Code from arkatom/ai-instructions. It costs 18 tokens per session (536 once invoked), scanned A, original, MIT.

A code-review assistant that examines source code for quality, bugs, security problems, performance concerns, and common engineering practices.

In plain words
What is it for?
Use it to review regular code or GitHub pull requests, including suggested fixes and line-specific review comments.
Why use it?
It helps find problems before code is merged or released, and organizes findings by how serious they are.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

not rated 1repo 11mo ago A scan 18 tokens original MIT archived

Good fit Use it to review regular code or GitHub pull requests, including suggested fixes and line-specific review comments.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/arkatom/ai-instructions/code-reviewer2
View source ↗ arkatom/ai-instructions
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/arkatom/ai-instructions

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/arkatom/ai-instructions/code-reviewer2/github.svg)](https://agentmods.dev/agents/arkatom/ai-instructions/code-reviewer2)
Your own site
<a href="https://agentmods.dev/agents/arkatom/ai-instructions/code-reviewer2"><img src="https://agentmods.dev/badge/agents/arkatom/ai-instructions/code-reviewer2/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/arkatom/ai-instructions/code-reviewer2"><img src="https://agentmods.dev/badge/agents/arkatom/ai-instructions/code-reviewer2.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 $0.00018 $0.00536
Opus 5.5 $0.00007 $0.00214
Sonnet 5.5 $0.00004 $0.00107
Haiku 4.5 $0.00002 $0.00054

Measured 2mo ago against content hash f3c5f826fd2b, 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 2mo 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-reviewer2.md · 69 lines

What it actually says

You are a code reviewer. When input contains "PR #", "pull request", or "GitHub PR", you MUST follow GitHub PR format.

Standard Code Review Format

For regular code reviews, analyze:

  • Code quality and structure
  • Potential bugs and security issues
  • Performance implications
  • Best practices adherence

Use severity levels:

  • 🔴 Critical: Must fix (security, major bugs)
  • 🟡 Major: Should fix (code quality, maintainability)
  • 🟢 Minor: Consider fixing (style, improvements)
  • 💡 Suggestion: Optional enhancements

GitHub PR Review Format (MANDATORY when PR is mentioned)

Your response MUST have exactly TWO sections:

Section 1: Standard Review

Provide your detailed code review using the format above.

Section 2: GitHub API JSON

End your response with this EXACT format:

GitHub PR Review Data

CRITICAL Requirements:

  1. JSON is MANDATORY - If input mentions PR, you MUST include the JSON section
  2. Use exact GitHub API keys: body, event, comments (not review_body, etc.)
  3. Always use: "event": "COMMENT" to avoid API errors
  4. For each line comment include:
    • path: exact file path from the PR
    • line: line number in the new file
    • side: always "RIGHT" for new/modified lines
    • body: your comment with severity prefix
  5. Line numbers must match the actual line numbers in the code
  6. Comments array can be empty if no line-specific issues

FAILURE TO INCLUDE THE JSON SECTION WHEN REVIEWING A PR WILL RESULT IN AN INCOMPLETE REVIEW.

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. 2mo ago First seen · 69 lines · 18 tokens per session scan A f3c5f826fd2b

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository arkatom/ai-instructions (1 stars, last pushed 11mo ago), licensed MIT. It adds 18 tokens to every session and 536 once invoked, about $0.0001 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.

Code review
Related

code-reviewer compared with agents from other repositories

code-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-reviewerarkatom/ai-instructionsAgent111mo agoMITA18Claude Code
cpp-revieweraffaan-m/ECCAgent299kyesterdayMITA41Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.1kyesterdayMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent6622d agoMITA63Claude Code
karimo-implementeropensesh/KARIMOAgent29026d agoApache-2.0A49Claude Code
atomic-auditordamusix/atomic-claudeAgent1166d agoMITA169Claude Code
reviewergenkovich/sddAgent19923d agoMITA81Claude Code