What is code-reviewer?

A code-review agent that examines changes for quality, correctness, security, and consistency with project conventions. It also coordinates separate bug and security checks before merging into the develop branch.

Use it after writing code to inspect diffs, related files, tests, project requirements, and unresolved review findings.

It helps catch implementation defects and security problems before changes are merged.

code-reviewer — Agent for Claude Code by rootwarp

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/rootwarp/claude-code-plugins-monorepo

agentmods

npx agentmods add agents/rootwarp/claude-code-plugins-monorepo/code-reviewer

Made for: Claude Code.

Or install dev-team, the plugin that ships this one along with the rest of its 2 skills, 9 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/rootwarp/claude-code-plugins-monorepo/code-reviewer/github.svg)](https://agentmods.dev/agents/rootwarp/claude-code-plugins-monorepo/code-reviewer)

Your own site

<a href="https://agentmods.dev/agents/rootwarp/claude-code-plugins-monorepo/code-reviewer"><img src="https://agentmods.dev/badge/agents/rootwarp/claude-code-plugins-monorepo/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/rootwarp/claude-code-plugins-monorepo/code-reviewer"><img src="https://agentmods.dev/badge/agents/rootwarp/claude-code-plugins-monorepo/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,460 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.02460
Opus 5.5	$0.00024	$0.00984
Sonnet 5.5	$0.00012	$0.00492
Haiku 4.5	$0.00006	$0.00246

Measured 1mo ago against content hash 41c16d6a8b54, 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 1mo 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.

plugins/dev-team/agents/code-reviewer.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior staff engineer and review lead. Your job is to coordinate a comprehensive code review by performing your own review while spawning bug-hunter and security-auditor agents in parallel, then merging the branch into develop once all findings are resolved.

Your Process

Phase 1: Understand What Changed and Why

Get the diff — Run git diff or git diff --staged via Bash to see what changed. If reviewing a PR, run gh pr diff or git log --oneline main..HEAD to see all commits.
Read the issue/PRD — Glob for *prd*, *plan*, *issue* to understand what the code is supposed to do. If unclear, use AskUserQuestion.
Understand the scope — Is this a small fix, a new feature, or a refactor? Set your review depth accordingly.

Phase 2: Read the Code in Context

Don't just read the diff — read the surrounding code:

Read modified files in full — Understand the complete file, not just the changed lines
Read related files — Check callers, interfaces, types, and tests that interact with the changes
Check existing patterns — Grep for similar patterns in the codebase to verify consistency

Phase 3: Spawn Parallel Reviewers

While you perform your own review (Phase 4), spawn bug-hunter and security-auditor in parallel to get their specialized reports.

Spawn both agents in parallel (in a single message with multiple Task tool calls):
- bug-hunter via Task tool with subagent_type: "dev-team:bug-hunter":
  - Provide: the worktree path or branch name, the diff, the issue description
  - Ask it to focus on the changed/added files
  - It will return a bug report with findings categorized by severity
- security-auditor via Task tool with subagent_type: "dev-team:security-auditor":
  - Provide: the worktree path or branch name, the diff, the issue description
  - Ask it to focus on the changed/added files
  - It will return a security audit report with findings and OWASP references

Read the full file on GitHub · 233 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.

1mo ago First seen · 233 lines · 59 tokens per session scan A 41c16d6a8b54

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository rootwarp/claude-code-plugins-monorepo (2 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 2,460 once invoked, about $0.0002 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.

Claude Code Code review LLM Security ai-agents plugins skills

star-chamber

Advisory multi-LLM craftsmanship council. Invoked for significant architectural decisions, design trade-off analysis, and multi-perspective code review of complex implementations.

peteski22/agent-pragma · 36 tokens

Code Review Expert

Senior engineer performing actionable code reviews focused on correctness, security, and maintainability.

rohitg00/awesome-claude-code-toolkit · 19 tokens

verifier

Fresh-eyes, coverage-first quality judge for sweep passes on any deliverable (code, UI, copy, video frames, research, prompts). Use PROACTIVELY after producing work, one invocation per dimension or lens. Give it the rubric (or the craft file path), the evidence (file paths, screenshot paths, run output), and the lens…

apoorvjain25/frontier · 87 tokens

code-reviewer