review-code

review-code is a command for Claude Code from kumaran-is/claude-code-onboarding. It costs 25 tokens per session (701 once invoked), scanned A, original, MIT.

A tracing command for one RAG query, recording what happened across the retrieval-and-answer pipeline. The trace can be used to investigate a failure or create a regression test.

In plain words
What is it for?
It is for debugging one query, checking access-control behavior, collecting audit evidence, and adding a known failure to a test set.
Why use it?
It replaces guesswork with a detailed record of a problematic request, including pipeline stages and user context. RAG means retrieving documents to help an AI model answer a question.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/kumaran-is/claude-code-onboarding/review-code
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-code

README.md
[![agentmods](https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/review-code.svg)](https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/review-code)
Your own site
<a href="https://agentmods.dev/commands/kumaran-is/claude-code-onboarding/review-code"><img src="https://agentmods.dev/badge/commands/kumaran-is/claude-code-onboarding/review-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 701 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 5.1 $0.00025 $0.00701
Opus 5 $0.00013 $0.00351
Sonnet 5 $0.00005 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 3d ago against content hash 00f540f0d797, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-code 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 3d 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.

.claude/commands/review-code.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Review the specified code for quality, security, and maintainability using parallel multi-perspective review.

Process

Step 1 — Detect scope

Determine which files/directories to review from $ARGUMENTS (default: recent changes via git diff --name-only HEAD).

Step 2 — Identify active stacks

Scan the file list for tech signals and build a dispatch list:

Signal Agent
*.java or pom.xml spring-reactive-reviewer
*.ts + NestJS decorators (@Controller, @Injectable, @Module) nestjs-reviewer
*.ts/*.html under Angular project (angular.json present) code-reviewer (Angular)
*.dart or pubspec.yaml riverpod-reviewer
*.py + LangChain/LangGraph imports agentic-ai-reviewer
*.py (other) code-reviewer (Python)
*.sql or migration files postgresql-database-reviewer
Mixed/other code-reviewer (general)

Always add: security-reviewer — runs on ALL scopes regardless of stack.

Step 3 — Dispatch in parallel

Launch all identified agents simultaneously using the Task tool with run_in_background: true. Do not wait for one to finish before starting the next.

Example for a NestJS + database change:

  • Background agent 1: nestjs-reviewer — NestJS-specific quality checks
  • Background agent 2: postgresql-database-reviewer — SQL/migration safety
  • Background agent 3: security-reviewer — auth, injection, secrets

Step 4 — Merge findings by severity

Collect all agent outputs and produce a unified report. De-duplicate issues that multiple agents flagged independently (keep the most specific description).

## Review: [scope] — [N] agents, [N] files

### CRITICAL (must fix before merge)
- [file:line] [agent] [description]

### HIGH (strongly recommended to fix)
- [file:line] [agent] [description]

### MEDIUM (fix soon, can merge with justification)
- [file:line] [agent] [description]

### LOW / INFO (consider for future)
- [file:line] [agent] [description]

### Summary
- Agents dispatched: [list]
- Total issues: N  (critical: X, high: Y, medium: Z, low: W)
- Duplicate findings collapsed: N
- Verdict: ✅ APPROVE / ⚠️ NEEDS_REVIEW / ❌ REJECT

Verdict rules:
  ✅ APPROVE     — 0 critical, 0 high unresolved
  ⚠️ NEEDS_REVIEW — 0 critical, ≥1 high (must justify in PR)
  ❌ REJECT       — ≥1 critical unresolved

Read the full file on GitHub · 74 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. 3d ago First seen · 74 lines · 25 tokens per session scan A 00f540f0d797

Subscribe to this mod's changes

review-code is a command published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 701 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 2026-09-03.