Front-End Checklist
The essential checklist for modern web development, for humans and AI agents.
- Source repo
- thedaviddias/Front-End-Checklist
- Stars
- ★ 75k
- Last updated
- 12d ago
- License
- MIT
- Primary language
- MDX
- FA score
- 37/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platform
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A front-end developer uses the checklist to self-audit a new page before deployment, ensuring performance and accessibility standards are met.
- Not a fit if
- Teams that need fully offline review, since the public MCP server sends code or URLs externally
- Teams needing non-English rules, as the rule corpus is English-only
- Teams requiring a clear license for commercial use, as none is declared
- Source review
- 37/100 · Major gaps 4 safety controls not found
What does this agent do, and when should you use it?
Front-End Checklist is an open-source front-end quality system that provides 385 English rules across 11 active categories, including HTML, CSS, JavaScript, performance, accessibility, SEO, security, images, testing, privacy, and internationalization. It offers multiple modes of use: a website for browsing, an MCP server for agent integration, and a comprehensive README for offline reference. The project also ships reusable skills for automated audit workflows, making it a versatile tool for both manual review and AI-assisted code auditing.
The project delivers a structured set of front-end best-practice rules, each with explanations, remediation guidance, and verification steps. Via the MCP server, AI agents can invoke 11 tools such as review_code, search_rules, audit_url, get_workflow, and get_checklist_rules to review pasted code, audit live URLs, fetch specific rules, or obtain audit workflows. The website frontendchecklist.io enables interactive browsing and filtering, while the local development setup uses pnpm commands for contributing and validation.
- A front-end developer uses the checklist to self-audit a new page before deployment, ensuring performance and accessibility standards are met.
- An AI agent integrated with the MCP server reviews a React component and reports the highest-confidence front-end issues.
- A QA engineer runs the checklist against a live site to identify SEO and performance regressions.
- A team uses the prioritized rules as a code review checklist for pull requests.
- An educator incorporates the checklist into a web development course to teach best practices.
How do you install or deploy this agent?
No installation is required for website or MCP server. To contribute or run locally, clone the repository and run pnpm install, then pnpm dev for development. Skills can be installed via npx skills add frontendchecklist/skills.
How do you use this agent?
Visit frontendchecklist.io/rules to browse rules, or connect an MCP-capable agent to mcp.frontendchecklist.io. Use commands like review_code for pasted code, search_rules for rule lookup, and audit_url for public URL audits. For skills, install and invoke SKILL.md files for global audits or focused rules like https.
What are this agent's strengths and limitations?
- Comprehensive rule corpus (385 rules) with priority levels (Critical, High, Medium, Low).
- MCP server enables direct integration with AI agents for automated audits.
- Multiple access modes: website, MCP, README, and skills for flexibility.
- Actively maintained with companion project UX Patterns for Devs.
- Large rule set may overwhelm new users; requires filtering.
- Rules are solely in English, limiting accessibility for non-English speakers.
- Public MCP server may raise data privacy concerns for proprietary code.
- No explicit license, which could restrict commercial use or redistribution.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Front-End Checklist This agent | 37 · Major gaps | Web appFree | ★ 75k | 12d ago | MDX | — |
| SquirrelScan | 67 · Some gaps | CLIFreemium | ★ 286 | 1d ago | TypeScript | Codex · Claude Code |
| Argot Repository Style Analyzer | 93 · Excellent | CLIFree | ★ 51 | 1mo ago | Rust | Claude Code |
| Happier | 82 · Good | Desktop appFree + model costs | ★ 2k | today | TypeScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows a monorepo with an MCP server providing tools like review_code, but no explicit permission model or user confirmation mechanism. Data flow transparency is limited; telemetry is anonymous but not detailed. Sensitive data handling not mentioned. Dependency security has Trivy scan but no results. External effects not specified. Rollback not mentioned. Source attribution partial, rules have URLs but provenance unclear.
Self-consistency is good with tests and CI, but dependency availability unverified, failure messages present in test timeouts but overall error handling unclear.
Audience clearly front-end developers, scenarios include checklists and code review. Capability boundaries reflected in MCP tool descriptions, but trigger precision insufficient, environment fit depends on Node version and pnpm.
Information architecture clear with README and TOC. Install notes exist but brief. Naming stability moderate, version exists but no changelog. Examples and FAQ partial. Known limitations not explicit. License not mentioned. Maintenance responsibility unclear.
Output usability good with structured content. Marginal value high with checklists and MCP tools. Cost-benefit not assessed but dependencies numerous.
Claim traceability moderate, rules have URLs but sources not explicit. Cross-source corroboration limited. Fact-inference separation unclear.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: disclosed external effectsEstablish which external systems it writes to, sends to or changes, and verify with test accounts or repos before production.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- License information not provided; confirm before use.
- MCP server permission model unclear, potential over-privilege.
- Numerous dependencies, supply chain security concern.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.