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 eric861129/SKILLS_All-in-one --skill email-html-mjmlgit clone --depth 1 https://github.com/eric861129/SKILLS_All-in-oneWrote 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/eric861129/skills_all-in-one/email-html-mjml)<a href="https://agentmods.dev/skills/eric861129/skills_all-in-one/email-html-mjml"><img src="https://agentmods.dev/badge/skills/eric861129/skills_all-in-one/email-html-mjml/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/eric861129/skills_all-in-one/email-html-mjml"><img src="https://agentmods.dev/badge/skills/eric861129/skills_all-in-one/email-html-mjml.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 | $0.00084 | $0.01992 |
| Opus 5 | $0.00042 | $0.00996 |
| Sonnet 5 | $0.00017 | $0.00398 |
| Haiku 4.5 | $0.00008 | $0.00199 |
Grade A, and why
email-html-mjml 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 9d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
email-html-mjml — Responsive Email Developer
Generate valid, cross-client MJML 4.x templates and compile them to production-ready HTML. The primary goal is compatibility: Outlook (2013–365), Gmail (web/app), Apple Mail, and major mobile clients. Every output must be compilable with --config.validationLevel=strict and survive Gmail's 102KB clip limit.
Workflow
- Gather requirements — Infer email type, brand colors, and content from the user's message and conversation context. Ask only for what is genuinely missing and blocking progress (e.g., no colors provided and the layout has branded sections). Never front-load a questionnaire.
- Plan layout — Decide and announce the structure before writing code (single-column, 2-col grid, hero + content, etc.)
- Load component references — Read the relevant file(s) from the Component Index below before writing any MJML
- Generate MJML — Write complete, valid MJML starting from
<mjml>with a full<mj-head> - Compile — Follow
compilation.md. Runnpx mjmlwith--config.minify=true - Deliver both files — Always output
.mjmlsource AND compiled.html
9 Engineering Rules
- Structural Integrity — All visual content MUST be in
<mj-column>inside<mj-section>. Sections cannot be nested. - Responsive Defaults — Assume 600px width. Use
<mj-group>to prevent mobile stacking for side-by-side elements (social bars, logo rows). - Outlook Compatibility — Use
<mj-font>for web fonts (prevents Times New Roman fallback). Always provide a fallback stack (Arial, sans-serif). For<mj-section>background images, always set bothbackground-sizeand a fallbackbackground-color. - Gmail Optimization — Use
inline="inline"on<mj-style>for custom CSS. Prefer component attributes (color,font-size) over CSS classes for critical styles. - Dark Mode — Include dark mode support when explicitly requested or when the email has a light background that would cause harsh forced-inversion. See the Dark Mode Pattern below.
- Accessibility — Every
<mj-image>MUST havealt. Always set<mj-title>(populatesaria-label). Maintain WCAG 2.1 AA 4.5:1 contrast. For heading roles, usemj-html-attributes— directrole/aria-levelattributes onmj-textare illegal under strict validation (see Accessibility Checklist below). - Styling Efficiency — Use
<mj-attributes>with<mj-all>, component defaults, and<mj-class>to eliminate repetitive inline styles. - Hero Sections — Use
<mj-hero>for full-bleed hero banners; it falls back to a regular section in unsupported clients. Avoid<mj-accordion>and<mj-carousel>— client support is too poor to be useful. - Templating Support — Wrap dynamic tags (Handlebars/Liquid) in
<mj-raw>to protect them from the MJML parser.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 162 lines · 84 tokens per session scan A 26928413802a
email-html-mjml is a skill published in the GitHub repository eric861129/SKILLS_All-in-one (52 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 1,992 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
frontend-design
Use when user asks to build a web component, page, or application, or when the task involves frontend design, HTML/CSS generation, or UI layout. Applies specific rules for typography, OKLCH color, layout, motion, interaction, and UX writing to produce distinctive, production-grade interfaces that avoid generic AI…
ui-ux-design
Create production-grade frontend interfaces with strong UX and visual craft. Use when building web components, pages, dashboards, forms, landing pages, modals, or any UI. Use when user says 'build a form', 'create a dashboard', 'design a component', 'make a landing page', or asks for UI/UX work. Use even when the user…
frontend-craft-director
A self-contained frontend design, redesign, audit, implementation, anti-AI-slop, and rendered visual-QA skill for use directly inside a ChatGPT conversation or through a local MCP-accessible project.
ds-guard
Automatically run after any edit to a .css, .tsx, .ts, .jsx, or .js file that contains styling. Triggers on: new CSS rules, className changes, style props, token usages, or any visual/layout change. Checks the diff against the project's design system token inventory and living style guide (canon, if one exists). Flags…
openclaw-color-palette
Design-grade color processing suite — generate harmonious palettes from any seed color, check WCAG 2.1 AA/AAA contrast accessibility, convert between hex/RGB/HSL/HSV/CMYK, simulate 8 color blindness types, and extract dominant colors from images. Use when: (1) user says 'generate a color palette' or 'give me a color…
animate
Generate CSS/Framer Motion animations.