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 senderkit/senderkit-skills --skill senderkit-email-deliverabilitygit clone --depth 1 https://github.com/senderkit/senderkit-skillsWrote 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/senderkit/senderkit-skills/senderkit-email-deliverability)<a href="https://agentmods.dev/skills/senderkit/senderkit-skills/senderkit-email-deliverability"><img src="https://agentmods.dev/badge/skills/senderkit/senderkit-skills/senderkit-email-deliverability/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/senderkit/senderkit-skills/senderkit-email-deliverability"><img src="https://agentmods.dev/badge/skills/senderkit/senderkit-skills/senderkit-email-deliverability.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 | $0.00167 | $0.01334 |
| Opus 5 | $0.00084 | $0.00667 |
| Sonnet 5 | $0.00033 | $0.00267 |
| Haiku 4.5 | $0.00017 | $0.00133 |
Grade A, and why
senderkit-email-deliverability 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 12d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SenderKit email deliverability
Use this open-source skill to get authenticated, inbox-landing transactional email. It diagnoses a sending domain's authentication, generates the exact DNS records to fix it, and verifies the result — using standard tools (dig/nslookup) that need no install, signup, or API key. The reusable source lives at https://github.com/senderkit/senderkit-skills in the skills/senderkit-email-deliverability/ directory; the skill name remains senderkit-email-deliverability.
Email authentication is required whether the app sends directly via SenderKit or routes through a provider (Resend, SendGrid, Postmark, Mailgun, SES, SMTP). This skill is provider-agnostic: it reads and fixes the DNS that controls inbox placement.
This skill does not change application code and does not edit DNS — it inspects DNS, produces records for the user to apply at their DNS host, and re-checks them. To wire sends into the codebase (From domain, headers) use senderkit-integration. To send a live test message and confirm placement use senderkit-mcp-messaging-operations.
Workflow
-
Identify the sending domain.
- Establish the exact
Fromdomain mail is (or will be) sent from, e.g.mail.example.comorexample.com. - If known, note the SenderKit DKIM selector and SPF include for the account; otherwise the user obtains these from the SenderKit dashboard (see step 4). Do not guess these values.
- Establish the exact
-
Diagnose current DNS. Read
references/spf-dkim-dmarc.mdfor syntax and limits, then query:- SPF:
dig +short TXT <domain>— flag a missing record, more than onev=spf1record, syntax errors, and the 10-DNS-lookup limit. - DKIM:
dig +short TXT <selector>._domainkey.<domain>— confirm the selector is published with ap=public key. - DMARC:
dig +short TXT _dmarc.<domain>— confirm presence and policy strength (p=nonevsquarantine/reject) and reporting (rua). - MX:
dig +short MX <domain>— sanity check. - Alignment: confirm SPF (
MAIL FROM/Return-Path) and DKIM (d=) align with the visibleFromdomain.
- SPF:
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.
- 12d ago First seen · 61 lines · 167 tokens per session scan A 907b7bcccaf4
senderkit-email-deliverability is a skill published in the GitHub repository senderkit/senderkit-skills (1 stars, last pushed 10d ago), licensed MIT. It adds 167 tokens to every session and 1,334 once invoked, about $0.0008 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
cpp-sanitizers
Use in C/C++ projects for crashes, hangs, UB, data races, memory errors. ASan/UBSan/TSan runtime checks. Build sanitizer config separately.
docs-lookup
Use when looking up unfamiliar tools, APIs, errors, library behavior. Context7 → WebSearch → calibrated uncertainty fallback chain. Don't guess.
self-correction-loop
Use when a hook/tool returns a warning, lint/type/build error, or test failure after your edit. Iterate evidence-first; stop when verification passes.
capturing-golden-rules
Use when the same mistake or bad pattern recurs, when a code-review comment is really a convention worth enforcing, or when you catch AI-generated drift/slop and want it to never happen again. Encodes the lesson as a durable rule in golden-rules.md — the feedback-flywheel / harness-layer-learning ratchet — instead of…
hooks
Generate YouTube video hooks using the Kallaway desire-based framework. Produces Three Hook Alignment (visual + spoken + text), applies the Four Commandments, maps to core desires, and scores each hook. Trigger on phrases like 'write a hook for', 'hook ideas for my video', 'help me with the intro', 'generate hooks'…
test-coverage-design
Use when deciding what to test, reviewing whether a feature is adequately covered before calling it done, or when tests pass but you're unsure they exercise the real risks. Derives coverage obligations from code + spec, finds gaps (including paths outside the test runner's scope), and designs a minimal…