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 bcharleson/cursor-for-gtm-demo --skill cold-email-copywritinggit clone --depth 1 https://github.com/bcharleson/cursor-for-gtm-demoWrote 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/bcharleson/cursor-for-gtm-demo/cold-email-copywriting)<a href="https://agentmods.dev/skills/bcharleson/cursor-for-gtm-demo/cold-email-copywriting"><img src="https://agentmods.dev/badge/skills/bcharleson/cursor-for-gtm-demo/cold-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/bcharleson/cursor-for-gtm-demo/cold-email-copywriting"><img src="https://agentmods.dev/badge/skills/bcharleson/cursor-for-gtm-demo/cold-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 | $0.00061 | $0.01588 |
| Opus 5.5 | $0.00024 | $0.00635 |
| Sonnet 5.5 | $0.00012 | $0.00318 |
| Haiku 4.5 | $0.00006 | $0.00159 |
Grade A, and why
cold-email-copywriting 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Copywriting
Cold email copy must be relevant, not relational. The prospect is a stranger — they do not care about small talk, shared alumni networks, or geographic coincidence. Value must be obvious in seconds.
Core Principle: The Stain Remover Pen
Imagine standing next to someone in an elevator who has a food stain on their white shirt they cannot see. You have a stain remover pen. You say:
"I noticed a stain on your shirt. I have a stain remover pen that'll take it out right now — want to try it?"
They immediately understand the pain, the fix, and the low effort to accept. No rapport required. Cold email works the same way — spot a real problem, offer a clear fix, make saying yes effortless.
What Never to Write
Reject and rewrite copy that includes:
- "I hope this email finds you well"
- "I love what you're doing at [company]"
- "Your profile is amazing"
- "I noticed we both went to [university]"
- "I'll be in your area next week"
- Generic compliments with no tied value
- Long paragraphs or essay-style pitches
- Obvious sales pressure — if they feel sold to, defenses go up
Merge Tags (Variables)
Merge tag syntax is tool-specific. Wrong casing means tags will not render and prospects see literal {{firstName}} in the inbox.
Default: camelCase — matches Instantly and most modern sequencers:
| Field | Tag |
|---|---|
| First name | {{firstName}} |
| Last name | {{lastName}} |
| Company | {{companyName}} |
| Sender first name | {{senderFirstName}} |
Before drafting or reviewing copy, confirm which sequencer or ESP the user sends from (e.g. Instantly, Smartlead, Lemlist, Outreach). Use that tool's exact tag names and casing. If unknown, default to camelCase and flag for the user to verify against their platform docs.
Never use snake_case (e.g. {{first_name}}) unless the user's tool explicitly requires it.
Email Structure
Every cold email follows four parts. Keep the full message short and mobile-optimized — readable on a phone without scrolling.
What ships with it
1 file 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.
- 2mo ago First seen · 172 lines · 61 tokens per session scan A 78dada00e00d
cold-email-copywriting is a skill published in the GitHub repository bcharleson/cursor-for-gtm-demo (2 stars, last pushed 4mo ago), licensed MIT. It adds 61 tokens to every session and 1,588 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.
cold-email-copywriting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cold-email-copywritingbcharleson/cursor-for-gtm-demo | Skill | 2 | 4mo ago | MIT | A | 61 | Cursor |
| cargo-orchestrationgetcargohq/cargo-skills | Skill | 21 | yesterday | MIT | A | 205 | Claude Code |
| cargo-aigetcargohq/cargo-skills | Skill | 21 | yesterday | MIT | A | 167 | Claude Code |
| cargo-hostinggetcargohq/cargo-skills | Skill | 21 | yesterday | MIT | A | 180 | Claude Code |
| cargo-contextgetcargohq/cargo-skills | Skill | 21 | yesterday | MIT | A | 162 | Claude Code |
| cargo-storagegetcargohq/cargo-skills | Skill | 21 | yesterday | MIT | A | 168 | Claude Code |
| cargo-workspace-managementgetcargohq/cargo-skills | Skill | 21 | yesterday | MIT | A | 151 | Claude Code |