What is email-compat?

A guide and checker for building HTML emails that display correctly in services such as Outlook, Gmail, and Apple Mail. It explains their differing HTML and CSS support and can check compatibility and finished markup.

For creating, editing, or reviewing HTML email templates and transactional messages, especially when targeting several email clients.

Email clients do not support web-page features consistently, so an email that looks right in one may break in another. The included checks help reveal those compatibility problems.

email-compat — Skill for Claude Code and Codex by shbernal

Install

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.

Any agent

npx skills add shbernal/caniemail-ai-tooling --skill skill

Clone the repo

git clone --depth 1 https://github.com/shbernal/caniemail-ai-tooling

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shbernal/caniemail-ai-tooling/skill/github.svg)](https://agentmods.dev/skills/shbernal/caniemail-ai-tooling/skill)

Your own site

<a href="https://agentmods.dev/skills/shbernal/caniemail-ai-tooling/skill"><img src="https://agentmods.dev/badge/skills/shbernal/caniemail-ai-tooling/skill/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.

Your own site · 80×15

<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="Reviewed on agentmods" width="80" height="20"></a>

Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,968 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.5	$0.00051	$0.00787
Sonnet 5.5	$0.00026	$0.00394
Haiku 4.5	$0.00013	$0.00197

Measured 1mo ago against content hash 04bd369ef719, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/caniemail-core.mjs, scripts/caniemail.mjs, scripts/css-scan.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skill/SKILL.md · 182 lines

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 24+ 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.

Read the full file on GitHub · 182 lines

Files

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.

Changes

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.

1mo ago Changed 04bd369ef719
1mo ago Changed a967af432860
2mo ago First seen · 182 lines · 128 tokens per session scan A 05e178ca85b0

Subscribe to this mod's changes

email-compat is a skill published in the GitHub repository shbernal/caniemail-ai-tooling (1 stars, last pushed 10d ago), licensed MIT. It adds 128 tokens to every session and 1,968 once invoked, about $0.0005 per session on Opus 5.5. 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.

CSS and styling Frontend agent-skills caniemail claude email email-compatibility html-email

email-compat next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
email-compatshbernal/caniemail-ai-tooling	Skill	1	10d ago	MIT	A	128	Claude Code, Codex
anti-slop-designsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	34	Claude Code
chakra-ui-builderchakra-ui/chakra-ui	Skill	41k	yesterday	MIT	A	214	Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codex	Skill	34k	3d ago	MIT	A	52	Codex
open-design-setupcompozy/compozy	Skill	2.8k	yesterday	MIT	A	67	Claude Code, Codex
edit-sitemicrosoft/power-platform-skills	Skill	1.1k	yesterday	MIT	A	104	Claude Code
frontend-visual-qadaymade/claude-code-skills	Skill	1.5k	yesterday	MIT	A	125	Claude Code, Codex