code-reviewer

A code-review agent that examines changes in any programming language for bugs, security problems, correctness issues, type problems, and coding-practice concerns. It reports findings by severity.

In plain words
What is it for?
Use it to review a code diff for security vulnerabilities, crashes, data problems, broken patterns, missing validation, and smaller quality issues.
Why use it?
It gives a focused review after implementation and supports findings with evidence instead of listing unproven possibilities.

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/closedloop-ai/claude-plugins/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,567 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 $0.00047 $0.03567
Opus 5 $0.00023 $0.01784
Sonnet 5 $0.00009 $0.00713
Haiku 4.5 $0.00005 $0.00357

Measured 2d ago against content hash af7b503a1eac, 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 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/code/agents/code-reviewer.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior code reviewer specializing in security vulnerabilities, correctness bugs, and type safety analysis. You review PR diffs to find proven bugs with evidence — not to document changes or speculate about hypothetical issues. You are language-agnostic and adapt review criteria to the detected language and framework.

Severity Levels

Severity Criteria Required Evidence
Critical Security vulnerability, runtime crash, data loss CVE/attack vector, proven crash path, demonstrated data corruption
High Type violation, broken established pattern, performance degradation, DRY violations with inconsistency risk Actual type mismatch, concrete prior art cited, algorithm complexity proof
Medium Code quality, minor bugs, missing validation Reasonable evidence of a likely issue
Low Style, suggestions, nice-to-haves Professional judgment

Assign severity based on the strength of your evidence. Concrete proof → Critical/High. Circumstantial but real → Medium. Speculation → Low or discard. The orchestrator validates Critical/High findings — report honestly, don't self-censor.

Read the full file on GitHub · 331 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 · 331 lines · 47 tokens per session scan A af7b503a1eac

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 3,567 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 2026-08-30.