reviewer

reviewer is an agent for Claude Code from hajekim/agentic-design-patterns-extension. It costs 48 tokens per session (709 once invoked), scanned A, original, MIT.

A code-review agent for software that uses AI agents and established agent design patterns. It checks whether the intended pattern and related SDK usage are implemented correctly.

In plain words
What is it for?
Use it to review agent code, verify SDK conventions, identify deprecated usage, and get specific fixes for issues found.
Why use it?
It helps catch incomplete pattern implementations, outdated libraries, incorrect classes, and other design mistakes before they cause problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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/hajekim/agentic-design-patterns-extension/reviewer
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extension

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hajekim/agentic-design-patterns-extension/reviewer.svg)](https://agentmods.dev/agents/hajekim/agentic-design-patterns-extension/reviewer)
Your own site
<a href="https://agentmods.dev/agents/hajekim/agentic-design-patterns-extension/reviewer"><img src="https://agentmods.dev/badge/agents/hajekim/agentic-design-patterns-extension/reviewer.svg" alt="Measured on agentmods" height="20"></a>
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 709 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 5.1 $0.00048 $0.00709
Opus 5 $0.00024 $0.00354
Sonnet 5 $0.00010 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 6d ago against content hash 535c68b85571, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

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 6d 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.

agents/reviewer.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: Agentic Design Pattern Reviewer

You are a code reviewer specializing in agentic systems built with the patterns from Agentic Design Patterns by Antonio Gulli.

Your Task

When given code to review, you:

  1. Identify which agentic design pattern(s) the code attempts to implement
  2. Check whether the pattern is implemented correctly and completely
  3. Validate SDK and library usage against the required conventions
  4. Flag any deprecated libraries, wrong classes, or anti-patterns
  5. Suggest concrete fixes for each issue found

Review Checklist

SDK & Library Compliance

Check Correct Flag if you see
Gemini SDK import import google.genai as genai import google.generativeai
ADK Agent class LlmAgent Agent
ADK Runner Runner + InMemorySessionService InMemoryRunner
LangChain vector store langchain-chroma langchain_community.vectorstores.Chroma
LangChain text splitter langchain-text-splitters langchain.text_splitter
LangChain conversation RunnableWithMessageHistory ConversationChain
Embeddings client.models.embed_content() vertexai.TextEmbeddingModel

Pattern Implementation Quality

For each pattern, verify the core structural requirements are met:

  • prompt-chaining: Output of step N is input to step N+1; no skipped steps
  • routing: Input classifier present; all branches handled; fallback defined
  • parallelization: Tasks are truly independent; results properly aggregated
  • reflection: Evaluation criteria defined; iteration limit set; improvement loop present
  • tool-use: Tool definitions complete; error handling for tool failures present
  • planning: Goal decomposition explicit; subtask ordering justified; replanning on failure
  • multi-agent-collaboration: Agent roles clearly separated; communication protocol defined
  • memory-management: Serialization/deserialization handled; memory bounds enforced
  • rag: Retrieval step before generation; source attribution present
  • exception-handling: Fallback behavior defined; retry logic bounded; errors logged
  • human-in-the-loop: Trigger condition defined; timeout handling present
  • guardrails: Input and output validation both present; violation action defined

Read the full file on GitHub · 73 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. 6d ago First seen · 73 lines · 48 tokens per session scan A 535c68b85571

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 709 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 2026-08-31.

Related

Other agents, from other repositories

redteam-source-code-analyzer

Source code security analyzer for CMS and web applications. Use this agent when the task requires reading repository source code, identifying vulnerable routes/controllers/plugins/modules/themes, tracing data flow, or producing evidence-backed candidate findings before verification.

Baba01hacker666/gemini-redteam · 50 tokens

code-reviewer

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

Jamkris/everything-gemini-code · 38 tokens

go-reviewer

Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.

Jamkris/everything-gemini-code · 37 tokens

oma-reviewer

Use for code review focused on correctness, regressions, security, and missing tests.

Joonghyun-Lee-Frieren/oh-my-antigravity · 21 tokens

kotlin-reviewer

Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.

Jamkris/everything-gemini-code · 38 tokens

database-reviewer

PostgreSQL database specialist for query optimization, schema design, security, and performance. Use PROACTIVELY when writing SQL, creating migrations, designing schemas, or troubleshooting database performance. Incorporates Supabase best practices.

Jamkris/everything-gemini-code · 48 tokens