first-touch

first-touch is a skill for Claude Code from Frontal-so/outbound-skills. It costs 112 tokens per session (875 once invoked), scanned A, original, MIT.

A cold-email writing skill for the first message in a business-to-business sales campaign. It uses short plain-text emails with one request and chooses from several established message structures.

In plain words
What is it for?
Use it to draft an initial outreach email, choose a message framework, identify a reason to contact someone now, and write a 60–90 word first touch.
Why use it?
It provides a repeatable way to turn a target customer, a timely reason to contact them, and a relevant problem into an opening email. This helps avoid unfocused introductions or emails that lead with product features.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to draft an initial outreach email, choose a message framework, identify a reason to contact someone now, and write a 60–90 word first touch.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frontal-so/outbound-skills/first-touch
Install

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.

Any agent
npx skills add Frontal-so/outbound-skills --skill first-touch
Clone the repo
git clone --depth 1 https://github.com/Frontal-so/outbound-skills

Made for: Claude Code.

Wrote 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.

agentmods badge for first-touch

README.md
[![agentmods](https://agentmods.dev/badge/skills/frontal-so/outbound-skills/first-touch/github.svg)](https://agentmods.dev/skills/frontal-so/outbound-skills/first-touch)
Your own site
<a href="https://agentmods.dev/skills/frontal-so/outbound-skills/first-touch"><img src="https://agentmods.dev/badge/skills/frontal-so/outbound-skills/first-touch/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.

agentmods 80×15 button for first-touch

Your own site · 80×15
<a href="https://agentmods.dev/skills/frontal-so/outbound-skills/first-touch"><img src="https://agentmods.dev/badge/skills/frontal-so/outbound-skills/first-touch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 875 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.00875
Opus 5 $0.00056 $0.00438
Sonnet 5 $0.00022 $0.00175
Haiku 4.5 $0.00011 $0.00088

Measured 9d ago against content hash 8c85ebb29f7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

first-touch 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 9d 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.

master-skills/cold-email/.claude/skills/first-touch/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

First Touch Email Writing

You write high-performing first cold emails for B2B outbound. Every email must be 60-90 words, plain text, one CTA, and lead with pain over features.

Process

  1. Clarify ICP -- Ask: Who is the target? (title, company size, industry). ATL or BTL?
  2. Identify trigger -- What signal or reason justifies reaching out NOW?
  3. Select framework -- Pick from the 8 allowed frameworks below
  4. Draft email -- 60-90 words, one soft CTA, specific social proof

Reference

Read {SKILL_BASE}/resources/frameworks/writing-frameworks.md for all 8 frameworks and Josh Braun principles. Read {SKILL_BASE}/resources/templates/email-templates-library.md for 23 first-touch templates and the 7 Frontal Email 1 variations. Read {SKILL_BASE}/resources/frameworks/copywriting/frontal-playbook.md for 3 value prop styles (Show Cost, Peer Proof, Specific Outcome), 3 preview/first line patterns (Observation, Pain, Industry), and Frontal benchmarks from 250K+ emails.

8 Allowed Frameworks

  1. Before/After -- Show current state vs. desired state
  2. Pattern Interrupt -- Break expectations to earn attention
  3. Ask Before Pitch -- Open-ended question before any selling
  4. Upfront Value -- Give something useful before asking
  5. Do the Math -- Trigger + pitch + calculation + CTA
  6. Challenge of Similar Companies -- "Companies doing X in Y often struggle with Z"
  7. Neutral Insight -- Share third-party resource, build trust first
  8. Typical Problems by Role -- Role-specific pain that prompts reflection

Structure Checklist

Opening (trigger/observation) + Assumption + Social proof with numbers + Open-ended question
  • 60-90 words max
  • No bullets in cold emails
  • One CTA only -- soft ask ("Worth a quick look?" not "Book a 30-min demo")
  • Specific social proof ("47% increase" not "significant improvement")
  • Lead with pain, not features
  • Plain text only

Examples

Example 1: Do the Math framework for a hiring platform

Subject: 12 open roles

{{firstName}}, quick math:

{{company}} has 12 engineering roles open averaging 45 days to fill.

At $500/day in lost productivity, that's $270K sitting on the table.

We helped {{similar_company}} cut time-to-fill by 38%.

Want to see the breakdown?

Read the full file on GitHub · 96 lines

Changes

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.

  1. 9d ago First seen · 96 lines · 112 tokens per session scan A 8c85ebb29f7f

Subscribe to this mod's changes

first-touch is a skill published in the GitHub repository Frontal-so/outbound-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 875 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

audience-icp-filter

Filter an existing audience or lead list against your ICP and split it into ready-to-sequence segments. Use when someone already has a list of people — an audience in their sales tool, a CSV or CRM export, event or webinar attendees, registrants, a Sales Navigator import, a newsletter or community export — and wants…

LaGrowthMachine/gtm-system · 228 tokens

team-performance-dashboard

Generate your Team Performance Dashboard from your La Growth Machine data: a head-of-sales cockpit that ranks each sender (rep) on reply rate, your success event (signups/meetings/deals) and conversion, surfaces hot leads going cold, and turns your best reps' campaigns into a coaching playbook for the rest. Pulls only…

LaGrowthMachine/gtm-system · 235 tokens

weekly-performance-advisor

Generate your Weekly Performance Advisor dashboard from your La Growth Machine data: a two-tab cockpit (To do + Weekly performance) that flags campaigns to fix, sorts replies by urgency, and tracks reply volume week over week. It pulls only YOUR live LGM data, scores each running campaign against baked 3-zone…

LaGrowthMachine/gtm-system · 215 tokens

objection-analyzer

Find out which objections your outbound gets, how well your team handled them, and what to say next time. Use whenever the user wants to analyze the objections in their replies, rank the most frequent ones, know how to handle a specific objection, coach reps on their objection answers, build an objection playbook or…

LaGrowthMachine/gtm-system · 215 tokens

sales-nav-search-builder

Generate a precise LinkedIn Sales Navigator search URL from a natural-language ICP description — for sales prospecting, outbound outreach, lead generation, and B2B targeting. Use whenever the user asks for a Sales Nav URL, a LinkedIn search URL, an outbound prospecting query, a search for a persona or role, wants to…

LaGrowthMachine/gtm-system · 221 tokens

won-deal-icp-finder

Audit your biggest closed-won deals to find your PROVEN ideal customer profile, then find more accounts like them. Use whenever someone wants to analyze won deals, audit their best customers, see which companies generated the most revenue, find their real ICP, build a look-alike target list, segment customers by what…

LaGrowthMachine/gtm-system · 220 tokens