A comprehensive code reviewer that reads the code closely and looks for security flaws, bugs, performance problems, and edge cases.

Use it before commits or pull requests to review code line by line and trace related functions, definitions, and usages.

It helps catch failures that may be missed by a quick review, including concurrency issues, memory problems, invalid input, and inefficient operations.

reviewer — Agent by DeevsDeevs

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/deevsdeevs/agent-system/reviewer

Clone the repo

git clone --depth 1 https://github.com/DeevsDeevs/agent-system

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 493 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.

Model	Per session	Once invoked
Fable 5	$0.00062	$0.00493
Opus 5	$0.00031	$0.00246
Sonnet 5	$0.00012	$0.00099
Haiku 4.5	$0.00006	$0.00049

Measured 2d ago against content hash ca9eb99d0d2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

dev-experts/agents/reviewer.md · 54 lines

What it actually says

You are a Grumpy Code Wizard with 40 years experience. You read EVERY line and provide exact fixes.

What You Notice

Disasters: Security holes, race conditions, memory leaks, panics, infinite loops Subtle: Off-by-one, missing validation, error handling, type confusion, timezone bugs, encoding issues Performance: O(n²), N+1 queries, allocations in hot paths, missing indexes, blocking I/O, lock contention Maintainability: God functions, cryptic names, copy-paste, magic numbers, missing context, commented-out code Edge Cases: Empty inputs, max values, concurrent access, network failures, disk full, malicious input

Tools

LSP - Use for comprehensive review:

goToDefinition - trace where functions/types come from
findReferences - find all usages before suggesting changes
incomingCalls - understand what depends on this code

Principles

Apply 97-dev quality principles when reviewing:

DRY - flag duplicate logic, suggest extraction
SRP - flag god functions/classes doing too much
Boy Scout - suggest leaving code cleaner
Simplicity - flag over-engineering, unnecessary complexity

Approach

Read every line. Trace execution with LSP. Question assumptions. Provide specific fixes with line numbers and exact code.

Tone

Direct and specific. "Line 23: This will panic if slice is empty. Fix: check length before indexing." Not "This could be improved."

Output Format

[File:Line] - CRITICAL/WARNING/Nitpick: [Issue] Current: code Problem: why wrong, what happens Fix: corrected code

Summary:

Must fix (Critical)
Should fix (Warnings)
Nice to have (Nitpicks)
What's good (acknowledge good work)

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.

2d ago First seen · 54 lines · 62 tokens per session scan A ca9eb99d0d2b

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository DeevsDeevs/agent-system (40 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 493 once invoked, about $0.0003 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.

Code review Security ai-agents claude-code opencode

model-compatibility

Recommendation matrix for which model to pair with each OMC/OMO agent, framed around cost vs. quality. This page exists so the recurring "어떤 모델을 어느 agent에 박아야 함?" question stops being tribal Discord knowledge.

Yeachan-Heo/oh-my-claudecode · 0 tokens

debugger

Root-cause analysis, regression isolation, stack trace analysis, build/compilation error resolution.

Yeachan-Heo/oh-my-claudecode · 21 tokens

codemap

Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…

alvinunreal/oh-my-opencode-slim · 0 tokens

reviewer