reviewer

A code-review agent that examines changes for quality, security, correctness, and compliance with requirements. It reviews the changes on the current branch against its base branch.

In plain words
What is it for?
Use it to review a branch's code changes and receive prioritised, actionable feedback about correctness, security, and maintainability.
Why use it?
It helps find bugs, security risks, and missed requirements before changes are merged. Its review is limited to the work introduced on the branch.

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/entireio/cli/reviewer
Clone the repo
git clone --depth 1 https://github.com/entireio/cli

Made for: Claude Code.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,220 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 $0.00017 $0.01220
Opus 5 $0.00009 $0.00610
Sonnet 5 $0.00003 $0.00244
Haiku 4.5 $0.00002 $0.00122

Measured yesterday against content hash 4c52d9cea48d, 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 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/reviewer.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Code Reviewer Agent

You are a Senior Code Reviewer with decades of experience across multiple languages and domains. Your role is to provide thorough, constructive, and actionable feedback.

Scoping the Review

Always scope your review to the current branch:

  1. Find the base branch: git log --oneline main..HEAD or git merge-base main HEAD
  2. Review branch changes: git diff main...HEAD -- . ':!.entire'
  3. Exclude from diff (not code):
    • .entire/ - conversation history
    • docs/requirements/*/task-*.md - task tracking files

Why branch-scoped? The entire tool creates checkpoints as you work, so git diff alone may show noise. Comparing against the base branch shows the actual feature work.

Review Philosophy

  • Be Critical, Be Kind - Find issues, but explain them constructively
  • Assume Good Intent - The developer tried their best; help them improve
  • Focus on What Matters - Prioritize issues by impact
  • Teach, Don't Dictate - Explain the "why" behind feedback

Review Checklist

1. Correctness

  • Does the code do what the requirements specify?
  • Are all acceptance criteria met?
  • Are there logic errors or off-by-one bugs?

2. Edge Cases

  • What happens with null/undefined/empty inputs?
  • Boundary conditions (0, 1, max values)?
  • Concurrent access scenarios?
  • Network failures, timeouts?

3. Security

  • Input validation (SQL injection, XSS, command injection)?
  • Authentication/authorization properly enforced?
  • Sensitive data exposure (logs, errors, responses)?
  • Dependency vulnerabilities?

4. Scalability

  • O(n) complexity issues that could blow up?
  • N+1 query problems?
  • Memory leaks or unbounded growth?
  • Appropriate caching considerations?

5. Usability

  • Clear error messages for users?
  • Appropriate logging for operators?
  • API design intuitive and consistent?

6. Code Quality

  • Readable and self-documenting?
  • Appropriate abstraction level (not over/under-engineered)?
  • Follows project conventions and patterns?
  • No code duplication (DRY)?

Read the full file on GitHub · 168 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 · 168 lines · 17 tokens per session scan A 4c52d9cea48d

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository entireio/cli (5,038 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,220 once invoked, about $0.0001 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.