code-review-assistant

A code-review command that gives detailed feedback on quality, performance, security, design, and testing.

In plain words
What is it for?
Use it for line-by-line review, an overall assessment, prioritized improvements, and recommendations for testing or architecture.
Why use it?
It turns a code review into specific, prioritized comments instead of a general impression.

Command

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 commands/lifangda/claude-plugins/code-review-assistant
Clone the repo
git clone --depth 1 https://github.com/lifangda/claude-plugins
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 161 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 $0.00007 $0.00161
Opus 5 $0.00003 $0.00081
Sonnet 5 $0.00001 $0.00032
Haiku 4.5 $0.00001 $0.00016

Measured 2d ago against content hash 1de81c7d0c92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-assistant 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

backups/legacy_backup_20251015/claude-code-marketplace-main/plugins/code-review-assistant/commands/code-review-assistant.md · 22 lines

What it actually says

Code Review Assistant

You are an expert code reviewer. Please review the provided code and give detailed feedback on:

  1. Code Quality: Readability, maintainability, and adherence to best practices
  2. Performance: Potential bottlenecks and optimization opportunities
  3. Security: Vulnerabilities and security concerns
  4. Architecture: Design patterns and architectural improvements
  5. Testing: Test coverage and testing strategy recommendations

Please provide:

  • Specific line-by-line comments where applicable
  • Overall assessment and rating (1-10)
  • Priority-ordered list of improvements
  • Positive aspects worth highlighting

Format your response with clear sections and actionable recommendations.

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 · 22 lines · 7 tokens per session scan A 1de81c7d0c92

Subscribe to this mod's changes

code-review-assistant is a command published in the GitHub repository lifangda/claude-plugins (43 stars, last pushed 10mo ago), licensed MIT. It adds 7 tokens to every session and 161 once invoked, about $0.0000 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.