workflow-review-code

A guided code review that checks a project’s structure, naming, TypeScript types, component design, data flow, imports, and dependencies against stated practices.

In plain words
What is it for?
Use it to review a codebase or proposed changes, especially projects using TypeScript, React Server Components, Server Actions, or tRPC.
Why use it?
It gives developers a consistent way to spot design problems, weak typing, messy organization, and unsafe patterns before they become harder to fix.

Command for Claude Code

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/rcdelacruz/claude-code-agents/workflow-review-code
Clone the repo
git clone --depth 1 https://github.com/rcdelacruz/claude-code-agents

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,965 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 $0.00009 $0.01965
Opus 5 $0.00005 $0.00983
Sonnet 5 $0.00002 $0.00393
Haiku 4.5 $0.00001 $0.00197

Measured 2d ago against content hash dc7885842577, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-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 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.

.claude/commands/workflow-review-code.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are in CODE REVIEW MODE.

Use code-reviewer agent to perform thorough code quality analysis.

Review Process

1. Initial Assessment (5 mins)

  • Review overall code structure
  • Check file organization
  • Assess naming conventions
  • Verify TypeScript usage

2. Architecture Review (10 mins)

Component Architecture

  • Server vs Client Components used correctly
  • Props properly typed with interfaces
  • Components are focused and single-purpose
  • Proper separation of concerns

Data Flow

  • Data fetching in Server Components
  • Mutations via Server Actions or tRPC
  • State management appropriate for use case
  • No prop drilling (use Context or state management)

Code Organization

  • Files in correct directories
  • Consistent naming (camelCase, PascalCase, kebab-case)
  • Imports organized (React, libraries, local)
  • No circular dependencies

3. TypeScript Review (10 mins)

Type Safety

// ❌ BAD: Any types
function processData(data: any) { }

// ✅ GOOD: Proper types
function processData(data: User) { }

// ❌ BAD: Type assertions
const user = data as User

// ✅ GOOD: Type guards
if (isUser(data)) {
  // data is User
}

Type Coverage

  • No any types (except unavoidable cases)
  • Functions have return type annotations
  • Interfaces defined for complex objects
  • Generics used where appropriate
  • Type guards for runtime checks

4. React Best Practices (15 mins)

Hooks Usage

// ❌ BAD: Conditional hooks
if (condition) {
  useEffect(() => { })
}

// ✅ GOOD: Hooks at top level
useEffect(() => {
  if (condition) { }
}, [condition])

// ❌ BAD: Missing dependencies
useEffect(() => {
  fetchData(userId)
}, []) // userId missing!

// ✅ GOOD: All dependencies
useEffect(() => {
  fetchData(userId)
}, [userId])

Component Patterns

  • Hooks only in components/custom hooks
  • Proper dependency arrays in useEffect
  • Memoization used appropriately (useMemo, useCallback)
  • No inline function definitions in JSX (if used in deps)

Read the full file on GitHub · 324 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 · 324 lines · 9 tokens per session scan A dc7885842577

Subscribe to this mod's changes

workflow-review-code is a command published in the GitHub repository rcdelacruz/claude-code-agents (2 stars, last pushed 10mo ago), licensed MIT. It adds 9 tokens to every session and 1,965 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 2026-08-31.