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 Ken-Technology/cold-email-skills --skill email-copywritinggit clone --depth 1 https://github.com/Ken-Technology/cold-email-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/ken-technology/cold-email-skills/email-copywriting)<a href="https://agentmods.dev/skills/ken-technology/cold-email-skills/email-copywriting"><img src="https://agentmods.dev/badge/skills/ken-technology/cold-email-skills/email-copywriting/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/ken-technology/cold-email-skills/email-copywriting"><img src="https://agentmods.dev/badge/skills/ken-technology/cold-email-skills/email-copywriting.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 | $0.00095 | $0.08438 |
| Opus 5 | $0.00048 | $0.04219 |
| Sonnet 5 | $0.00019 | $0.01688 |
| Haiku 4.5 | $0.00010 | $0.00844 |
Grade A, and why
email-copywriting scanned grade A with 1 finding 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 11d 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.
Asks the agent to reveal its instructionslowSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
- Every AI variable used (e.g. `{{First Line}}`) must have a matching H3 in `prompts.md`. `{{Subject Line}}` is the exception you don't have to write: many personalization stacks auto-emit a Subject Line output prompt fo Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How to write copy
Output Contract
emails_v2.md (and emails.md) must follow a fixed structure so downstream campaign tooling can parse them reliably. Hard rules this skill must honor:
## Email N: {Descriptive Title}- the title is the sequence step name (truncated to 25 chars). Missing title → step name falls back toVariant A.### Variant A (desc)/### Variant B (desc)- literal wordVariant, neverVersion(tools should warn onVersion). Letter inA..D. Parenthetical description becomes the step-name suffix.- Combined step name
{title} - {variant_desc}must be ≤25 chars. Longer strings get truncated - authors should pre-shorten to preserve intent. - AI variables use double braces
{{Title Case}}(uppercase-first required):{{First Line}},{{PS Line}},{{Subject Line}}. This is the canonical form for personalization tools and LLMs. (Legacy[Title Case]square brackets are still often auto-converted, but write{{...}}in all new copy.) - Lead variables use
{camelCase}:{firstName},{company}. Never{first_name}. - Signatures use the system variable
{sender_signature}(single braces) in place of any hand-written sign-off - on every email. See the Signature rule below. - Never write
{{tracking_link:...}}in local copy - write raw URLs or markdown links; tracking wrappers are tool-side if used. - End the file with a terminator H2 (
## Notes,## Signature Block,## AI Personalization Placeholders) so trailing metadata doesn't get swallowed into the last email's body. Also supported:**Variant Notes**:/**Test Notes**:inline markers. - Every AI variable used (e.g.
{{First Line}}) must have a matching H3 inprompts.md.{{Subject Line}}is the exception you don't have to write: many personalization stacks auto-emit a Subject Line output prompt for it (keptto_rewrite=0, so it's generated but never rewritten). Add a### Subject LineH3 only when you want to override the default.
Overview
This skill provides comprehensive guidance for writing effective cold email copy. Use this skill when creating email sequences, writing cold outreach, or reviewing email campaigns. Claude should reference these guidelines whenever writing or reviewing cold email copy.
What ships with it
11 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.
- 11d ago First seen · 548 lines · 95 tokens per session scan A c1e97f3362ae
email-copywriting is a skill published in the GitHub repository Ken-Technology/cold-email-skills (3 stars, last pushed 14d ago), licensed MIT. It adds 95 tokens to every session and 8,438 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
outbound-strategy
Build your own in-house cold email / outbound infrastructure instead of renting Smartlead, Instantly or Lemlist. Use when someone wants to set up self-hosted cold outreach: connecting their own SMTP/IMAP inboxes, sourcing and segmenting B2B leads, writing multi-step sequences, sending at scale with deliverability-safe…
cold-email-onboarding
First-run interactive setup for the cold-email skill pack. Walks the operator through brand-config.json (ICP, PSP, EVP, tone, infrastructure) and SOUL.md (voice fingerprints, banned phrases, stories you lean on) in 10 minutes. Refuses to let the operator skip — generic output is worse than no output. Loaded…
cold-email-audit
30-point audit of a B2B outbound program across four dimensions — infrastructure (8 points), targeting (8 points), messaging (8 points), and operations (6 points). Produces a 0-100 score, the top 3 levers, and a 90-day remediation order. Loaded by the main cold-email skill when the user asks to audit or grade their…
cold-email-deliverability
15-point pre-campaign domain health check across DNS (SPF, DKIM, DMARC, MX, BIMI), reputation (SNDS, Postmaster, blacklists), warm-up status (mailbox age, send volume ramp, reply ratio), and content (spam-trigger lint, link-to-text ratio, image-to-text ratio). Returns a 0-100 deliverability score and a fix-order. Uses…
cold-email-kickoff
Adaptive router for the cold-email skill pack. Detects the operator's current state (brand-config present? SOUL.md present? infrastructure ready? PSP defined? EVP locked? first campaign run?) and picks the next-best step. Loaded by the main cold-email skill on bare invocation ("/cold-email") or when the operator asks…
cold-email-list-quality
Score a cold-email prospect list 0-100 across dedup, role-fit (vs brand-config.icp), signal freshness, email-validity heuristics, exclusion-criteria match, and company-stage match. Returns the score, list of rows to remove, and a fix recommendation. Loaded by cold-email-weekly-rhythm on Monday's list refresh. Operates…