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 agentmods add skills/nicepkg/ai-workflow/cold-outreach-generatornpx skills add nicepkg/ai-workflow --skill cold-outreach-generatorgit clone --depth 1 https://github.com/nicepkg/ai-workflowWrote 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/nicepkg/ai-workflow/cold-outreach-generator)<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/cold-outreach-generator"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/cold-outreach-generator.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 | $0.00034 | $0.00955 |
| Opus 5 | $0.00017 | $0.00477 |
| Sonnet 5 | $0.00007 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
cold-outreach-generator 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Outreach Message Generator
Get responses. Book calls. Win clients.
What This Skill Does
Input: Target industry + your solution Output: Cold email templates, LinkedIn messages, follow-up sequences
Cold Email Formula (That Works)
Subject: [Specific Pain Point Question] Example: "Managing 200+ inspections/month in Excel?"
Body (5 sentences max):
Sentence 1: Specific observation about their business "I noticed [Company] handles fire inspections for commercial buildings in [City]."
Sentence 2: Common pain point "Most inspection companies I work with struggle with [specific problem]."
Sentence 3: Brief solution hint "I build custom software that [specific benefit]."
Sentence 4: Social proof "Built similar system for [Company] - saved them 15 hours/week."
Sentence 5: Soft CTA "Worth a 15-min call to see if this makes sense for you?"
Signature [Your Name] [Your Title] [Calendar Link]
LinkedIn Connection Message
"Hi [Name], I work with [industry] companies to solve [specific problem]. Thought it might be worth connecting."
Follow-up after connection: "Thanks for connecting! I noticed [Company] does [their work]. Quick question - how do you currently handle [their pain point]? Most [industry] businesses I talk to struggle with that."
Follow-Up Sequence
Day 0: Initial outreach Day 3: "Hi [Name], following up on my note from Monday. Curious if [pain point] is something you're dealing with?" Day 7: "Last note from me! If [problem] isn't a priority right now, no worries. But if it is, happy to show you what we built for [Similar Company]."
Stop after 3 touches. Don't be annoying.
What Gets Responses
✅ Specific: "Managing HVAC service calls" not "running your business" ✅ Relevant: Mention their actual work ✅ Brief: 5 sentences max ✅ Social proof: Name similar companies you helped ✅ Easy CTA: Calendar link, not "let me know when you're free"
What Kills Response Rates
❌ Generic: "I help businesses save time and money" ❌ Long: 3+ paragraphs ❌ Salesy: "Limited time offer! Act now!" ❌ Desperate: "Please respond!" ❌ Hard pitch: Pricing and features in first email
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.
- 5d ago First seen · 138 lines · 34 tokens per session scan A 8f3c2081ff4b
cold-outreach-generator is a skill published in the GitHub repository nicepkg/ai-workflow (283 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 955 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
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
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.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…