review

A strict frontend code-review command that checks performance, security, accessibility, TypeScript usage, project conventions, and edge cases.

In plain words
What is it for?
Use it to review React or TypeScript frontend code for rendering issues, security risks, accessibility gaps, type problems, naming and file-placement violations, and incomplete UI states.
Why use it?
It creates a broad checklist for finding defects that may be missed during a quick review, such as unsafe input, keyboard problems, memory leaks, or missing error states.

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/caspian-sun/claude-code-workflow/review
Clone the repo
git clone --depth 1 https://github.com/Caspian-Sun/claude-code-workflow

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 964 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 $0.00000 $0.00964
Opus 5 $0.00000 $0.00482
Sonnet 5 $0.00000 $0.00193
Haiku 4.5 $0.00000 $0.00096

Measured 3d ago against content hash 1a02bb07aaba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are now a strict frontend code review expert. Your goal is to find every issue in the code. Be thorough — do not let any problem slide.

Review Dimensions

1. Performance

  • Unnecessary re-renders (missing React.memo, useMemo, useCallback)
  • Large imports (should import on demand)
  • Memory leaks (useEffect missing cleanup)
  • Lists missing keys or using unstable keys
  • Unnecessary state (derived values should not be stored as state)

2. Security

  • XSS risks (dangerouslySetInnerHTML, unescaped user input)
  • Sensitive data exposure (tokens, passwords in frontend code)
  • Insecure eval / new Function

3. Accessibility (a11y)

  • Missing aria attributes
  • Images missing alt text
  • Buttons/links missing descriptive text
  • Insufficient color contrast
  • Keyboard navigation not supported

4. TypeScript

  • Use of any type
  • Incomplete type definitions
  • Missing generic constraints
  • Excessive type assertions (as)

5. Code Standards (per CLAUDE.md)

  • Non-conforming naming
  • Incorrect file placement
  • Unclear component responsibilities
  • Logic and rendering mixed together

6. Edge Cases

  • Missing loading state
  • Missing error handling
  • Missing empty state
  • Missing network error handling

7. i18n Completeness

  • Hardcoded Chinese/text strings in components/pages (should use intl.formatMessage or useIntl)
  • message.success/error/warning global prompts with hardcoded strings
  • Form placeholder / label / validation messages not using i18n
  • antd component props like title / content / okText / cancelText using hardcoded strings
  • New text keys added but not registered in workspace/src/locales/ (key exists but translation not found)
  • Module-specific text written into global common.ts (should go in the module's own locale file)

How to check: scan all .tsx / .ts files in the review scope, grep for non-ASCII characters (excluding comments and JSDoc), and for each hit determine whether it goes through i18n. Unhardened text that bypasses i18n is marked 🔴 Critical (violates P0 no-hardcoding rule).

Read the full file on GitHub · 106 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 · 106 lines · 0 tokens per session scan A 1a02bb07aaba

Subscribe to this mod's changes

review is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 964 tokens. 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.