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 messagebird/bird-ai --skill email-auditgit clone --depth 1 https://github.com/messagebird/bird-aiWrote 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/messagebird/bird-ai/email-audit)<a href="https://agentmods.dev/skills/messagebird/bird-ai/email-audit"><img src="https://agentmods.dev/badge/skills/messagebird/bird-ai/email-audit/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/messagebird/bird-ai/email-audit"><img src="https://agentmods.dev/badge/skills/messagebird/bird-ai/email-audit.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 | $0.00040 | $0.01852 |
| Opus 5.5 | $0.00016 | $0.00741 |
| Sonnet 5.5 | $0.00008 | $0.00370 |
| Haiku 4.5 | $0.00004 | $0.00185 |
Grade A, and why
email-audit 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 2mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email authentication audit
bird email tools audit <domain> resolves a domain's live email-authentication records — DMARC, SPF, DKIM, BIMI, MX — validates each, checks how they work together, and returns a graded report. Your job with this skill is to run it and then act as the consultant: read the findings, explain what each means in plain terms, and give the user a prioritized plan.
It is DNS-only and needs no auth. It sends no mail and inspects no message; it reads what the domain publishes.
bird email tools audit acme.com
bird email tools audit acme.com --selector s1 # also check a DKIM selector (see DKIM below)
MCP: email_tools_audit with { "domain": "acme.com", "selector": "s1" }.
When to use this vs the per-record validators
audit <domain>— "how is my domain set up?" Resolves live records and grades the whole posture. This is the one to reach for when someone describes a symptom ("going to spam", "failing DMARC", "can people spoof us?").validate-dmarc/validate-bimi <record>— "is this record I wrote correct?" Offline, parses a pasted string. Use when drafting a record before publishing, not when diagnosing a live domain.
If they give you a domain, audit it. If they paste a record, validate it.
Reading the report
{
"domain": "acme.com",
"valid": false, // true only when there are NO problem-severity findings
"records": [ // what was found, per area
{ "area": "dmarc", "found": true, "value": "v=DMARC1; p=none; rua=..." },
{ "area": "spf", "found": true, "value": "v=spf1 include:... ~all" },
{ "area": "dkim", "found": false, "value": null },
...
],
"findings": [ // graded observations, most-severe first
{ "severity": "problem", "area": "spf", "message": "...", "fix": "..." },
{ "severity": "warning", "area": "dmarc", "message": "...", "fix": "..." }
],
"recommendations": [ "...", "..." ] // the fixes, problems first — the action list
}
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.
- 2mo ago Changed · -157 tokens per session 36930bebcf66
- 2mo ago First seen · 97 lines · 197 tokens per session scan A 0436dca7cc22
email-audit is a skill published in the GitHub repository messagebird/bird-ai (9 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 1,852 once invoked, about $0.0002 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.
email-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| email-auditmessagebird/bird-ai | Skill | 9 | yesterday | MIT | A | 40 | Claude Code |
| telnyx-iot-curlteam-telnyx/ai | Skill | 225 | yesterday | MIT | A | 45 | Claude Code |
| telnyx-account-reports-curlteam-telnyx/ai | Skill | 225 | yesterday | MIT | A | 32 | Claude Code |
| telnyx-networking-curlteam-telnyx/ai | Skill | 225 | yesterday | MIT | A | 35 | Claude Code |
| telnyx-sip-curlteam-telnyx/ai | Skill | 225 | yesterday | MIT | A | 39 | Claude Code |
| telnyx-twilio-migrationteam-telnyx/ai | Skill | 225 | yesterday | MIT | A | 93 | Claude Code |
| telnyx-ai-inference-curlteam-telnyx/ai | Skill | 225 | yesterday | MIT | A | 39 | Claude Code |