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 koinod/koino-skills --skill cold-email-writergit clone --depth 1 https://github.com/koinod/koino-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/koinod/koino-skills/cold-email-writer)<a href="https://agentmods.dev/skills/koinod/koino-skills/cold-email-writer"><img src="https://agentmods.dev/badge/skills/koinod/koino-skills/cold-email-writer/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/koinod/koino-skills/cold-email-writer"><img src="https://agentmods.dev/badge/skills/koinod/koino-skills/cold-email-writer.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 | $0.00000 | $0.01383 |
| Opus 5 | $0.00000 | $0.00691 |
| Sonnet 5 | $0.00000 | $0.00277 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
cold-email-writer 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 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.
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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Writer
Write personalized cold emails that get replies. 3-5 sentences. One CTA. No fluff.
Description
Cold Email Writer generates hyper-personalized outbound emails given a company name, industry, and pain point. Every email follows the P.A.S. + 1 CTA formula that top SDRs use to hit 15%+ reply rates. The output is ready to send — no editing required.
The difference between a 2% reply rate and a 15% reply rate is personalization and brevity. This skill handles both.
Activation
This skill activates when:
- The user wants to write a cold email or outbound message
- The user provides a prospect's company and wants to reach out
- The user asks for email copy, outreach templates, or cold outreach help
- The user mentions prospecting, outbound sales, or email campaigns
Trigger phrases: "write a cold email", "outreach email", "email this prospect", "cold outbound", "prospecting email", "reach out to", "email copy"
The P.A.S. + 1 CTA Formula
P — Personalized Opening (1 sentence)
Reference something specific about THEM. Not "I hope this finds you well." Something that proves you spent 30 seconds looking at their business.
Sources for personalization:
- Recent LinkedIn post or company announcement
- Their website copy or a specific product/service they offer
- Industry trend affecting their segment
- A mutual connection or shared community
- Their job title + likely daily pain
A — Agitate the Pain (1-2 sentences)
Name the specific problem they face. Make it visceral. Use their language, not yours.
S — Solution Tease (1 sentence)
Hint at how you solve it. Do NOT explain your full solution. Create curiosity.
1 CTA — One Clear Ask (1 sentence)
One question. Low friction. Easy to say yes to.
Good CTAs: "Worth a 12-minute call this week?" / "Can I send a 2-minute video showing how?" / "Want me to run a free audit?"
Bad CTAs: "Let me know if you're interested" / "Would love to connect" / "Check out our website"
Instructions
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 · 137 lines · 0 tokens per session scan A 81e364d2bdf5
cold-email-writer is a skill published in the GitHub repository koinod/koino-skills (8 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,383 tokens. 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
capabilities
Your capability catalog — read this at boot. Lists the temporal date-range skills and the external integrations (reached via the loopback broker) available to you as a spawned worker, and exactly how to call each. Read-only. Consult it whenever you're unsure what tools/integrations you have or how to invoke them.
temporal
Resolve ANY named time window — today, yesterday, thisWeek, lastWeek, last7Days, last30Days, last90Days, thisMonth, lastMonth, thisQuarter, lastQuarter, thisYear, lastYear, last12Months — or an arbitrary range (lastNdays / lastNweeks / lastNmonths) to a concrete ISO date range relative to your run time. Read-only: no…
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
thisQuarter
Resolve "thisQuarter" to a concrete ISO date range relative to your run time — this quarter so far (quarter start → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a quarter-to-date task (QTD…
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…