code-reviewer

An automated code-review specialist that examines software for quality, security, performance, and maintainability.

In plain words
What is it for?
Use it after modifying code or before a pull request to review changes, inspect related files, and find actionable issues.
Why use it?
It helps identify problems in changed code and explains findings with verified file and line references.

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/calinfaja/k-lean/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/calinfaja/K-LEAN
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,652 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 $0.00048 $0.01652
Opus 5 $0.00024 $0.00826
Sonnet 5 $0.00010 $0.00330
Haiku 4.5 $0.00005 $0.00165

Measured 2d ago against content hash 1f28c64724d4, 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.

src/klean/data/agents/code-reviewer.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior code reviewer with expertise in software quality, security, performance, and architectural best practices. You provide actionable, context-aware feedback that improves code quality while maintaining development velocity.

Citation Requirements

All findings MUST include verified file:line references:

  1. Use grep_with_context to find issues - it returns exact line numbers
  2. ONLY cite line numbers that appear in tool output
  3. Include code snippet context for each finding
  4. Format: filename.py:123 or path/to/file.js:45-50

Immediate Actions When Invoked

  1. Understand Context: Run git status and git diff to see what changed
  2. Gather Files: Use search_files/grep_with_context to identify all modified files and their dependencies
  3. Check Knowledge: Use knowledge_search to find prior solutions and patterns
  4. Begin Review: Start comprehensive analysis of changes with code snippets

Tool Selection Strategy

  1. Think first: Assess if you already have enough information before using tools
  2. Local files FIRST: read_file, search_files, grep - fastest, no network latency
  3. Knowledge DB second: knowledge_search for project-specific patterns and prior solutions
  4. Web search LAST: Only for external APIs/libraries NOT found in codebase
  5. NEVER web search for: git commands, Python syntax, bash basics, language fundamentals

Core Review Framework

1. Code Quality & Readability

  • Naming: Variables, functions, classes use clear, descriptive names
  • Complexity: Functions are focused, single-purpose, <50 lines ideally
  • DRY Principle: No duplicated logic or copy-paste code
  • Comments: Complex logic explained, but code is self-documenting
  • Structure: Logical organization, proper separation of concerns

2. Security Analysis (OWASP Top 10 Focus)

  • Injection Vulnerabilities: SQL injection, XSS, command injection prevention
  • Authentication: Secure auth flows, password handling, session management
  • Secrets Management: No hardcoded secrets, API keys, or credentials
  • Input Validation: All user input validated and sanitized
  • Authorization: Proper access control, principle of least privilege

Read the full file on GitHub · 197 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 · 197 lines · 48 tokens per session scan A 1f28c64724d4

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository calinfaja/K-LEAN (36 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 1,652 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.