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 shbernal/caniemail-ai-tooling --skill skillgit clone --depth 1 https://github.com/shbernal/caniemail-ai-toolingWrote 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/shbernal/caniemail-ai-tooling/skill)<a href="https://agentmods.dev/skills/shbernal/caniemail-ai-tooling/skill"><img src="https://agentmods.dev/badge/skills/shbernal/caniemail-ai-tooling/skill.svg" alt="Measured on agentmods" 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 | $0.00128 | $0.01968 |
| Opus 5 | $0.00064 | $0.00984 |
| Sonnet 5 | $0.00026 | $0.00394 |
| Haiku 4.5 | $0.00013 | $0.00197 |
Grade A, and why
email-compat 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 7d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML email compatibility
Email clients are not browsers. Outlook on Windows renders with Microsoft Word,
Gmail strips <style> blocks in some contexts, and support for anything modern
is patchy and undocumented. This skill covers both halves of the problem. Write
markup that survives, then verify it against real data.
scripts/caniemail.mjs queries the caniemail.com dataset. Node 22+ and nothing
else, with no dependencies and no install step. It works offline against a
bundled dataset snapshot, and says so when it does.
node scripts/caniemail.mjs <command> [options]
Everything it prints is JSON.
The loop
Write using the rules below, then always lint before calling it done. The rules prevent the common failures; the linter catches the rest.
# 1. Find the slug. They are not guessable.
node scripts/caniemail.mjs search "rounded corners"
# -> css-border-radius
# 2. Decide how to build it.
node scripts/caniemail.mjs check css-border-radius --clients outlook.windows,gmail.*
# 3. Lint the finished email.
node scripts/caniemail.mjs lint --html draft.html --clients '*'
Reading a verdict
Four verdicts, and collapsing them is how confidently wrong advice happens.
| Verdict | Severity | What to do |
|---|---|---|
supported |
none | Use it. |
unsupported |
error |
It will not render. Use a fallback. |
mitigated |
warning |
Works with a documented workaround. Read notes, which is where the useful detail lives. |
untested |
unknown |
Nobody has tested it. This is not evidence of support, and not evidence against it. Avoid it, or test it yourself. |
untested is the one that matters most. It is not a soft unsupported and not
a soft supported; roughly a sixth of the whole matrix has no data at all.
Never report an untested feature as working.
Also check last_test_date and staleness. Some entries have not been retested
in five years, and the tool tells you when a verdict is old enough to distrust.
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.
- scripts/caniemail-core.mjs 34 KB runs code
- scripts/caniemail.mjs 4.5 KB runs code
- scripts/css-scan.mjs 12 KB runs code
- scripts/data/caniemail.json 641 KB
- scripts/detect.mjs 12 KB runs code
- scripts/feature-titles.mjs 19 KB runs code
- scripts/html-scan.mjs 9.1 KB runs code
- scripts/selector-shapes.mjs 7.5 KB runs code
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.
- 7d ago First seen · 182 lines · 128 tokens per session scan A 05e178ca85b0
email-compat is a skill published in the GitHub repository shbernal/caniemail-ai-tooling (1 stars, last pushed 3d ago), licensed MIT. It adds 128 tokens to every session and 1,968 once invoked, about $0.0006 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
waitlist-page
A simple waitlist page for collecting email addresses from people interested in a new product or early-access release.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…