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 cmj-hub/claude-cold-email --skill cold-email-deliverabilitygit clone --depth 1 https://github.com/cmj-hub/claude-cold-emailWrote 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/cmj-hub/claude-cold-email/cold-email-deliverability)<a href="https://agentmods.dev/skills/cmj-hub/claude-cold-email/cold-email-deliverability"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-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/cmj-hub/claude-cold-email/cold-email-deliverability"><img src="https://agentmods.dev/badge/skills/cmj-hub/claude-cold-email/cold-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 | $0.00134 | $0.01374 |
| Opus 5 | $0.00067 | $0.00687 |
| Sonnet 5 | $0.00027 | $0.00275 |
| Haiku 4.5 | $0.00013 | $0.00137 |
Grade A, and why
cold-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 2d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Deliverability — 15-point pre-campaign domain health
Loaded by cold-email when the user asks about deliverability,
SPF/DKIM/DMARC, domain health, or "are we ready to send."
Activation triggers
- "Check deliverability"
- "Domain health"
- "SPF / DKIM / DMARC"
- "Are we ready to send"
- "Pre-campaign check"
- "Why are we landing in spam"
- "Inbox placement"
Workflow
1. Inputs
Ask for:
sending_domain— e.g.outreach.jmc.comfrom_address— full address used in the From: headerinbox_provider— GSuite / O365 / Smartlead / Instantly / custommailbox_age_days— how long this address has been sendingcurrent_daily_send_volume— emails/dayrecent_reply_ratio— % over the last 14 days (skip if first campaign)
2. Run the 15 checks
The 15 checks span four categories:
| # | Category | Check | How |
|---|---|---|---|
| 1 | DNS | SPF record exists | dig TXT <domain> for v=spf1 |
| 2 | DNS | SPF includes inbox provider | Lookup includes match provider |
| 3 | DNS | SPF lookup count ≤10 | Resolve all includes recursively |
| 4 | DNS | DKIM selector resolves | dig TXT <selector>._domainkey.<domain> |
| 5 | DNS | DKIM key ≥1024 bits | Decode the p= value |
| 6 | DNS | DMARC record exists | dig TXT _dmarc.<domain> |
| 7 | DNS | DMARC policy ≠ none for cold outreach | p=quarantine or p=reject required for bulk senders post-Feb 2024 |
| 8 | DNS | DMARC has rua= reporting |
Aggregate report URI configured |
| 9 | Reputation | Domain not on Spamhaus / SURBL | Lookup against public blacklist APIs |
| 10 | Reputation | rDNS / PTR record matches sending IP | dig -x <sending-ip> matches forward |
| 11 | Warm-up | Mailbox age ≥21 days | Compare mailbox_age_days to threshold |
| 12 | Warm-up | Daily send ramp ≤30/day for first 14 days | Compare current_daily_send_volume |
| 13 | Warm-up | Reply ratio ≥3% over 14 days | (Hard threshold for B2B cold) |
| 14 | Content | TLS support on MX | Confirm STARTTLS advertised |
| 15 | Content | DKIM signs the body, not just headers | Test message via test tool (mxtoolbox) |
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.
- 2d ago Changed · -2 lines a8588abf22dd
- 11d ago First seen · 140 lines · 134 tokens per session scan A efb45fb76fb6
cold-email-deliverability is a skill published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 2d ago), licensed MIT. It adds 134 tokens to every session and 1,374 once invoked, about $0.0007 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
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
graphify
Knowledge graph engine for B2B sales intelligence. Builds queryable graphs from product catalogs, customer conversations, and market research. Powered by graphify.
telegram-toolkit
Register these commands with @BotFather using /setcommands.
lead-discovery
AI-driven lead discovery for B2B export. Searches web for potential buyers matching ICP, evaluates fit, and creates CRM records for follow-up.
b2b-sdr-agent
Open-source B2B AI SDR template. 7-layer context system with 10-stage sales pipeline, 4-layer anti-amnesia memory, 14 automated pipeline checks, WhatsApp IP isolation, multi-channel (WhatsApp+Telegram+Email). Built on OpenClaw.
sdr-humanizer
Transform AI-generated sales messages into natural, human-like conversations that build trust and rapport.