A command that reviews code changed during the current session, plus any files you specify. It checks coding practices, architecture, quality, security, performance, and tests.

Use it to review modified files or a feature for consistency with project patterns, appropriate error handling, missing tests, security concerns, and integration problems.

It helps identify issues in recent changes before they become harder to fix or affect other parts of the system.

code-review — Command by blencorp

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/blencorp/claude-code-kit/code-review

Clone the repo

git clone --depth 1 https://github.com/blencorp/claude-code-kit

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 496 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00496
Opus 5	$0.00006	$0.00248
Sonnet 5	$0.00002	$0.00099
Haiku 4.5	$0.00001	$0.00050

Measured 2d ago against content hash 334abcd960ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

code-review scanned grade B with 1 finding 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!cat "$CLAUDE_PROJECT_DIR/.claude/tsc-cache"/*/edited-files.log 2>/dev/null | awk -F: '{print $2}' | sort -u || echo "No files modified yet"

cli/core/commands/code-review.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer focused on quality, best practices, and system integration.

Context

Files modified this session (auto-generated):

!cat "$CLAUDE_PROJECT_DIR/.claude/tsc-cache"/*/edited-files.log 2>/dev/null | awk -F: '{print $2}' | sort -u || echo "No files modified yet"

User-specified additional files: $ARGUMENTS

Your Task

Review the code changes for:

Best Practices Adherence
- Code follows project patterns and conventions
- Proper error handling and logging
- Appropriate use of TypeScript types
- No code duplication or anti-patterns
Architectural Consistency
- Follows layered architecture (routes → controllers → services → repositories)
- Proper dependency injection usage
- Correct placement in project structure
- Integration with existing systems
Code Quality
- Clear, self-documenting code
- Appropriate comments where needed
- Performance considerations
- Security best practices
Testing Coverage
- Identify missing test cases
- Suggest edge cases to test
- Verify testability of new code

Instructions

Read the modified files from the auto-detected list and any user-specified files
Examine the implementation against project guidelines (check for SKILL.md files in .claude/skills/)
Use the Task tool to launch the code-architecture-reviewer agent with:
- subagent_type: code-architecture-reviewer
- description: review code changes
- prompt: List all modified files and ask the agent to review them for:
  - Code quality issues
  - Architectural concerns
  - Suggested improvements
  - Missing error handling or validation
  - Testing gaps
Summarize the agent's findings and create actionable recommendations

Quality Standards

Be specific about issues found (include file paths and line numbers)
Explain WHY something is an issue, not just WHAT
Provide concrete examples of how to fix issues
Prioritize findings (critical, important, nice-to-have)
Acknowledge good practices observed

Read the full file on GitHub · 66 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.

2d ago First seen · 66 lines · 12 tokens per session scan B 334abcd960ff

Subscribe to this mod's changes

code-review is a command published in the GitHub repository blencorp/claude-code-kit (101 stars, last pushed 9mo ago), licensed MIT. It adds 12 tokens to every session and 496 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review Security Testing

code-review

Getting it into your agent

What it costs to keep this loaded

Grade B, and why

Reads agent configuration directoriesmediumAgent snooping

How it starts

Context

Your Task

Instructions

Quality Standards

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement