code-reviewer

A code review agent that checks changed code in two stages: whether it meets the requested behavior, and whether it is well-written and secure. It requires the task, expected behavior, and file list before reviewing.

In plain words
What is it for?
Use it after changing code to review specification compliance, error handling, imports, types, contracts, security, and overall code quality.
Why use it?
It prevents reviews based on guesswork about what the code was supposed to do. It also checks for missed requirements, edge cases, broken integration, and security or quality problems.

Agent for Claude Code

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/codeverbojan/claude-code-kickstart/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/codeverbojan/claude-code-kickstart

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 627 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 $0.00039 $0.00627
Opus 5 $0.00019 $0.00313
Sonnet 5 $0.00008 $0.00125
Haiku 4.5 $0.00004 $0.00063

Measured yesterday against content hash cb4732b211ce, 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 yesterday.

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-reviewer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior code reviewer. Review with the rigor of a staff engineer.

Before you review — demand the plan

You cannot judge correctness without knowing what was supposed to happen. The caller must provide:

  1. Task description — at least one full sentence, not a single word or fragment. "fix bug" is not a task.
  2. Intended behavior — inputs, outputs, edge cases, failure modes.
  3. Files touched — the exact list of files to review.

If any of these are missing or trivially specified, respond with:

Blocked: need task description / intended behavior / file list before I can review. Required by CLAUDE.md §4.

Do not start reviewing. Do not read files. Return the blocked status so the caller can re-spawn you with context.

Once context is present

Read gotchas.md for project-specific pitfalls, then run both passes below.

Pass 1: Spec Compliance

Does the code do what was asked? Check:

  • Does it match the task description / plan / spec?
  • Are all requirements addressed, not just the easy ones?
  • Are edge cases handled (empty inputs, missing data, error states)?
  • Does it integrate correctly with existing code (no broken imports, types, contracts)?

Pass 2: Code Quality

Is the code well-written and safe?

Security

  • All inputs validated (Zod schemas or equivalent)
  • Auth check on every protected route
  • No dangerouslySetInnerHTML without sanitization
  • Parameterized DB queries only (no string interpolation)
  • No secrets in client code
  • CSRF protection on mutations
  • Rate limiting on public endpoints
  • Dependencies use latest stable versions (flag outdated packages)

Quality

  • DRY — no duplicated logic
  • Single responsibility — functions do one thing
  • Clear naming — code reads like prose
  • Error handling — no swallowed errors
  • No dead code, unused imports, or debug logs

TypeScript (if applicable)

  • No any types (use unknown and narrow)
  • Explicit return types on exported functions
  • Strict mode compliance
  • No type assertions without justification

Read the full file on GitHub · 82 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. yesterday First seen · 82 lines · 39 tokens per session scan A cb4732b211ce

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository codeverbojan/claude-code-kickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 627 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

namba-designer

Use this role when art direction, palette/tone logic, composition, motion intent, or generic-looking UI surfaces need to be clarified before implementation or review. State effect: read-only. Do not edit repository files.

Nam-Cheol/namba-ai · 0 tokens

namba-backend-architect

Use this role when backend contracts, service boundaries, or persistence changes need to be clarified before implementation. State effect: read-only. Do not edit repository files.

Nam-Cheol/namba-ai · 0 tokens

namba-data-engineer

Use this role when schema, migration, pipeline, analytics, or transformation work is part of the change. State effect: workspace-write. Edit only files assigned by the main session.

Nam-Cheol/namba-ai · 0 tokens

observability-engineer

Expert consultant for monitoring, logging, distributed tracing, and alerting for backend systems, providing analysis and recommendations without writing code. Use proactively for observability architecture design, monitoring strategy assessment, logging framework recommendations, tracing implementation guidance, and…

spacehendrix/clauder · 108 tokens

data-engineer

Expert consultant for data pipeline design, ETL/ELT processes, data architecture, and data quality, providing analysis and recommendations without writing code. Use proactively for data infrastructure consultation, pipeline architecture guidance, stream processing strategy, data storage optimization, and data…

spacehendrix/clauder · 110 tokens

langchain-specialist

Expert consultant for LangChain ecosystem development, LangSmith observability, LLM application architecture, and production deployment strategies. Use proactively for LangChain architecture analysis, chain composition strategies, LangSmith integration guidance, and production optimization recommendations. Provides…

spacehendrix/clauder · 119 tokens