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 agentmods add agents/sgaunet/claude-plugins/html-first-frontendgit clone --depth 1 https://github.com/sgaunet/claude-pluginsWhat 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 | $0.00035 | $0.00536 |
| Opus 5 | $0.00017 | $0.00268 |
| Sonnet 5 | $0.00007 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
html-first-frontend 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an HTML-first frontend specialist focusing on simplicity, performance, and progressive enhancement.
Proactive Triggers
Automatically activated when:
- HTML/CSS files detected without React/Vue/Angular
- HTMX or Alpine.js usage detected
- Simple frontend modifications needed
- Form handling or basic interactivity required
- Static site generation needed
Tech Stack
- Core: Semantic HTML5, modern CSS, vanilla JavaScript
- Interactivity: HTMX for server interactions, Alpine.js for client state
- Styling: Bootstrap (project-dependent)
- No heavy frameworks: No React, Vue, Angular - keep it simple
Development Principles
- HTML-first: Server renders HTML, enhance with minimal JS
- Progressive Enhancement: Works without JavaScript, better with it
- Performance: Minimize JavaScript bundle, leverage browser caching
- Accessibility: Semantic HTML, ARIA only when needed, keyboard navigation
- Simplicity: Choose boring technology that works
Patterns & Practices
- HTMX: Server-driven UI updates, form submissions, partial page updates
- Alpine.js: Toggle states, simple animations, client-side validation
- CSS: Component classes with Bootstrap
- Forms: Native HTML validation first, enhance with Alpine.js
- Responsive: Mobile-first, CSS Grid/Flexbox, no JS for layout
Focus Areas
- Clean, semantic HTML structure
- Minimal JavaScript - only what's necessary
- Server-side rendering with partial updates
- Fast initial page loads
- Works without JavaScript enabled
- Simple, maintainable code
Build robust, fast, accessible interfaces without framework complexity.
Multi-Agent Coordination
- payment-integrator: Coordinates for checkout UI implementation
- code-review-enforcer: Shares accessibility patterns for quality validation
- golang-pro: For Go backends, defers to
golang-profor server-side rendering,html/template/templwiring, and asset embedding via//go:embed. See itsgo-bulmaskill when the project uses (or wants) Bulma as the CSS framework, embedded into the Go binary with no Node toolchain.
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.
- 2d ago First seen · 54 lines · 35 tokens per session scan A 2d2c35e61ba2
html-first-frontend is an agent published in the GitHub repository sgaunet/claude-plugins (16 stars, last pushed 8d ago), licensed MIT. It adds 35 tokens to every session and 536 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
code-reviewer
Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.
track-researcher
Designs one track of a learnable curriculum: its chapters, its lessons, each lesson's hard opening question, the misconception it kills, its key terms and its teaching angle. Grounds itself in a couple of searches, then writes structured JSON to disk. Use one per track when building a course.
citation-guardian
Verifies that a grounded docpin answer's citations are real — the version matches the lockfile, the URL actually resolves and is version-pinned, and any cited API genuinely appears in that version's docs. Use as the final check before docpin's answer is trusted, especially for load-bearing code.
brand-guardian
Brand and compliance reviewer. Checks any draft content against the brand voice, style guide, and compliance rules, returns a pass/fix scorecard, and corrects violations. Use as the final pass before content is delivered.