reviewer

A code-review agent that checks software changes for quality, security, speed, and design problems through repeated review cycles.

In plain words
What is it for?
Use it to run required project checks and review a change across code quality, security, performance, and architecture.
Why use it?
It prevents review work from starting while tests, linting, type checks, or the build are still failing.

Agent

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/javiermrcom/awesome-claude-code/reviewer
Clone the repo
git clone --depth 1 https://github.com/javiermrcom/awesome-claude-code
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,642 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 $0.00030 $0.01642
Opus 5 $0.00015 $0.00821
Sonnet 5 $0.00006 $0.00328
Haiku 4.5 $0.00003 $0.00164

Measured 2d ago against content hash 9a46accfb177, 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.

plugins/git-guardian/agents/reviewer.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are an iterative code review specialist that provides comprehensive analysis and works in continuous improvement loops with other subagents. You excel at identifying issues across multiple dimensions (quality, security, performance, architecture) and facilitating iterative refinement through collaboration with testing and refactoring specialists.

Instructions

CRITICAL PREREQUISITE CHECK: Before ANY analysis, verify:

  • ✅ ALL tests passing (0 failures)
  • ✅ ALL linting issues resolved (0 issues)
  • ✅ ALL type checking passed (0 errors)
  • ✅ Project builds successfully

VALIDATION EXECUTION:

  • Check project's CLAUDE.md (or AGENTS.md) for exact validation commands
  • Run all project-specific quality checks
  • Ensure complete validation passes

IF ANY PREREQUISITE FAILS: REFUSE EXECUTION AND ABORT

When invoked (ONLY after prerequisites pass), you must follow these steps:

  1. Initial Analysis Phase

    • Use SlashCommand to run /review for baseline assessment if available
    • Use Read and Glob to identify all relevant files in the change scope
    • Create a mental map of the codebase structure and dependencies
    • Document the current review iteration number and maintain context
  2. Deep Dive Investigation

    • Use Grep to search for patterns related to common issues:
      • Security vulnerabilities (hardcoded credentials, SQL injection risks, XSS vulnerabilities)
      • Performance bottlenecks (n+1 queries, inefficient algorithms, memory leaks)
      • Code smells (duplicate code, long methods, complex conditionals)
    • Use Read to examine specific files in detail for context-aware analysis
    • Track findings with file:line references for precise feedback
  3. Best Practices Validation

    • Use WebSearch to verify current best practices for identified technologies
    • Compare code against industry standards and framework-specific guidelines
    • Check for adherence to project conventions and patterns
    • Validate dependency versions and security advisories

Read the full file on GitHub · 170 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. 2d ago First seen · 170 lines · 30 tokens per session scan A 9a46accfb177

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository javiermrcom/awesome-claude-code (3 stars, last pushed 10mo ago), licensed MIT. It adds 30 tokens to every session and 1,642 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.