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.
npx skills add theashishmaurya/pr-review-agent --skill frontendgit clone --depth 1 https://github.com/theashishmaurya/pr-review-agentWrote 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.
[](https://agentmods.dev/skills/theashishmaurya/pr-review-agent/frontend)<a href="https://agentmods.dev/skills/theashishmaurya/pr-review-agent/frontend"><img src="https://agentmods.dev/badge/skills/theashishmaurya/pr-review-agent/frontend/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/theashishmaurya/pr-review-agent/frontend"><img src="https://agentmods.dev/badge/skills/theashishmaurya/pr-review-agent/frontend.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00013 | $0.00571 |
| Opus 5 | $0.00006 | $0.00285 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
Frontend 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 10d 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.
What it actually says
Frontend Review Skill
Review React/TypeScript code for patterns, performance, and accessibility.
React Patterns
Hooks
- Correct dependency arrays in useEffect, useMemo, useCallback
- No stale closures in event handlers
- Custom hooks follow naming convention (use*)
- Rules of Hooks followed
State Management
- State minimized (derived values computed)
- Lifting state up when needed
- Proper use of context vs prop drilling
- State updates immutable
Performance
- React.memo when appropriate
- useMemo for expensive computations
- useCallback for event handlers passed to children
- List items have stable keys
- No inline object/array creation in render
Component Structure
- Single responsibility per component
- Component composition over inheritance
- Props interface defined for TypeScript
- Default values for optional props
TypeScript
- No
anytypes without justification - Proper null/undefined handling
- Generic constraints when needed
- Type guards for runtime checks
- Exported types for public APIs
Accessibility (a11y)
- Images have alt text
- Form inputs have labels
- Focus management
- ARIA attributes when semantic HTML insufficient
- Color contrast sufficient
- Keyboard navigation works
CSS/Styling
- No inline styles for dynamic values (use CSS variables)
- Responsive design for mobile
- No magic numbers (use design tokens)
- Proper z-index layering
Common Issues
Memory Leaks
// ❌ Missing cleanup
useEffect(() => {
subscribe(id, callback);
}, []);
// ✅ With cleanup
useEffect(() => {
return subscribe(id, callback);
}, []);
Stale State
// ❌ Stale closure
const handleClick = () => console.log(count);
// ✅ Use ref or state updater
const countRef = useRef(count);
const handleClick = () => console.log(countRef.current);
Severity Guide
🚨 Error: Runtime bugs, security issues, broken functionality ⚠️ Warning: Performance issues, anti-patterns 💡 Info: Style improvements, best practices
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.
- 10d ago First seen · 98 lines · 13 tokens per session scan A 9ad95cba3458
Frontend Review is a skill published in the GitHub repository theashishmaurya/pr-review-agent (2 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 571 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 2026-08-31.
Other skills, from other repositories
compiler-commit
Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits with the [compiler] or [rust-compiler] prefix.
compiler-verify
Use when you need to run all compiler checks (tests, lint, format) before committing. Detects whether TS or Rust code changed and runs the appropriate checks.
compiler-review
Review Rust port code for port fidelity, convention compliance, and error handling. Compares against the original TypeScript source.
ss-lint
Quick automated lint — detects common design system violations in seconds.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
frontend-code-review
Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.