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 humanizerai/agent-skills --skill cold-emailgit clone --depth 1 https://github.com/humanizerai/agent-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/humanizerai/agent-skills/cold-email)<a href="https://agentmods.dev/skills/humanizerai/agent-skills/cold-email"><img src="https://agentmods.dev/badge/skills/humanizerai/agent-skills/cold-email.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.00495 |
| Opus 5 | $0.00018 | $0.00247 |
| Sonnet 5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
cold-email 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 7d 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.
What it actually says
Write Cold Email
Generate a cold email that gets responses using proven copywriting frameworks.
Input
Parse $ARGUMENTS for:
- Target: Who they're emailing (role, company, industry)
- Goal: What they want (meeting, intro, feedback, sale)
- Context: Personalization hooks (mutual connection, recent news, specific pain point)
If arguments are incomplete, ask for the missing pieces.
Frameworks (Choose the best fit)
AIDA (Awareness → Interest → Desire → Action)
- Hook with relevance
- Build interest with value
- Create desire with proof/benefit
- Clear CTA
PAS (Problem → Agitate → Solution)
- Identify their problem
- Make it feel urgent
- Position as the solution
BAB (Before → After → Bridge)
- Their current state (problem)
- Their ideal state (outcome)
- How you bridge the gap
Hard Rules
- 50-125 words - Shorter emails get more replies
- Subject line: 3-5 words, lowercase, no clickbait
- First line: Personalized - reference something specific about them
- No fluff: Cut "I hope this email finds you well", "My name is...", "I wanted to reach out"
- One CTA: Single, specific ask (not "let me know if you're interested")
- Read time: Under 30 seconds
- Mobile-friendly: Short paragraphs, no walls of text
What Makes It Human
- Sounds like a real person, not a template
- Has a specific reason for emailing THIS person
- Shows you did research
- Doesn't oversell or use hype words
- Has a clear "what's in it for them"
Output Format
Subject: [subject line]
[Email body]
[First name only]
Framework used: [which one and why] Personalization: [what angle you used] Word count: [number]
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.
- 7d ago First seen · 70 lines · 36 tokens per session scan A 7a6431d1f528
cold-email is a skill published in the GitHub repository humanizerai/agent-skills (42 stars, last pushed 7mo ago), licensed MIT. It adds 36 tokens to every session and 495 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
humanizer-zh
Use when removing AI writing痕迹 from Chinese text to make it sound more natural and human-written.
humanizer
Use when transform AI-generated content into natural, human-sounding writing with proper tone and style. Use when working with humanizer.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.