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 gtm-skills/gtm --skill cold-email-fundamentalsgit clone --depth 1 https://github.com/gtm-skills/gtmWrote 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/gtm-skills/gtm/cold-email-fundamentals)<a href="https://agentmods.dev/skills/gtm-skills/gtm/cold-email-fundamentals"><img src="https://agentmods.dev/badge/skills/gtm-skills/gtm/cold-email-fundamentals/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/gtm-skills/gtm/cold-email-fundamentals"><img src="https://agentmods.dev/badge/skills/gtm-skills/gtm/cold-email-fundamentals.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 | $0.00054 | $0.00796 |
| Opus 5.5 | $0.00022 | $0.00318 |
| Sonnet 5.5 | $0.00011 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
cold-email-fundamentals 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 22d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Fundamentals
One email. Three beats. Under 80 words. The reader decides in four seconds whether this is about them or about you. Make it about them.
The three beats
- Observation. One specific thing about their company or role that is true today and that a stranger could not have pasted from a template. A hire, a launch, a job post, a pricing change, a quote they gave. Name it in one sentence. No "I noticed" or "I came across" — just state it.
- Relevance. One sentence connecting that observation to a problem people in their seat have. Not your product. The problem.
- Ask. One low-friction question they can answer with one word. Not "Do you have 30 minutes?" — "Is this on your plate this quarter?" or "Worth a look?"
Optional fourth line: one line of proof, only if it is a number or a name they would recognize. If you are not sure, cut it.
Rules
- Under 80 words. Count them.
- No greeting filler. No "I hope this finds you well." Start with the observation.
- No adjectives about yourself or your product. "Leading", "innovative", "seamless" — delete.
- No links in the first email. Links read as spam and kill deliverability.
- No calendar link. The ask is a question, not a booking.
- One idea. If you have two angles, write two emails and send one.
- Subject line: 2–5 words, lowercase, references the observation. It should look like an internal email. Examples:
the 3 new AE roles,re: pricing page change,your SaaStr talk. - Sign with first name and company. No title block, no logo, no quote.
- Write at an eighth-grade reading level. Short words beat long ones.
Process
- Ask the user for the observation if they did not give one. Do not invent facts about a real company. If they have none, help them find one: recent hires (job boards), funding (press), product changes (changelog, pricing page), executive moves (press release), customer reviews (G2, app stores).
- Identify the persona and the problem that persona owns. An SDR manager owns pipeline per rep; a VP Eng owns shipping velocity; a CFO owns cash and forecast accuracy.
- Draft the three beats. Then cut every word that does not earn its place.
- Check: Could this exact email be sent to anyone else? If yes, the observation is not specific enough. Start over.
- Return the subject line and the email. Then one line explaining the angle so the user can adjust it.
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.
- 22d ago First seen · 70 lines · 54 tokens per session scan A 34b6de94d195
cold-email-fundamentals is a skill published in the GitHub repository gtm-skills/gtm (188 stars, last pushed 23d ago), licensed MIT. It adds 54 tokens to every session and 796 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 2026-10-15.
cold-email-fundamentals compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cold-email-fundamentalsgtm-skills/gtm | Skill | 188 | 23d ago | MIT | A | 54 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |