sequence-writing

sequence-writing is a skill for Claude Code from Doris-Labs/sales-skills. It costs 72 tokens per session (1,398 once invoked), scanned A, original, MIT.

A guide for planning a multi-step sales outreach campaign across email, phone, and LinkedIn, with timing and a different reason for each contact.

In plain words
What is it for?
Use it to define a prospecting cadence, choose channels and spacing, personalize messages, vary the angle of each contact, and write a final breakup email.
Why use it?
It prevents repetitive follow-ups that give prospects no new reason to respond. Each touch adds a new insight, proof point, resource, or question.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sales-skills plugin — 30 skills shipped together

Good fit Use it to define a prospecting cadence, choose channels and spacing, personalize messages, vary the angle of each contact, and write a final breakup email.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/sequence-writing
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 Doris-Labs/sales-skills --skill sequence-writing
Clone the repo
git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

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 sequence-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/sequence-writing/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/sequence-writing)
Your own site
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/sequence-writing"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/sequence-writing/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 sequence-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/sequence-writing"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/sequence-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,398 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 $0.00072 $0.01398
Opus 5 $0.00036 $0.00699
Sonnet 5 $0.00014 $0.00280
Haiku 4.5 $0.00007 $0.00140

Measured 10d ago against content hash 5d13fca448bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sequence-writing 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 10d 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.

skills/sequence-writing/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sequence Writing

Purpose

Turn a target persona and a reason-to-reach-out into a complete multi-touch cadence: the right channel mix, the right spacing, a different angle on every touch, and a breakup that creates urgency — so the prospect hears a campaign, not eight copies of the same email.

Inputs

  • Who you're reaching (persona, role, company, segment)
  • The trigger or reason to reach out (event, pain, mutual deal context)
  • Channels available (email, phone, LinkedIn) and how aggressive the motion can be
  • Any known personalization hooks (recent meeting, prior deal, shared connection)

Method

A sequence is a story told across touches. The unit of design is the touch — each one has a channel, a time, and a single angle. Two rules govern the whole thing.

The value-per-touch rule: every touch must add something the prospect didn't have before — a new insight, a different proof point, a relevant resource, a question they haven't been asked. "Just bumping this" / "circling back" / "did you see my email" are not touches; they are noise that trains the prospect to ignore you. If a touch has no new angle, delete it.

Channel mix: alternate channels so you're not a single muted inbox thread. Email carries the substance; phone creates a live moment; LinkedIn warms and humanizes. A multi-threaded prospect who has seen you in three places replies more than one hit eight times in the same place.

Concrete cadence (8 touches over ~18 business days):

# Day Channel Angle
1 Day 1 Email Trigger + one specific hypothesis about their pain. One ask.
2 Day 1 LinkedIn Connection request, no pitch — reference the trigger in the note.
3 Day 3 Call + voicemail Reference touch 1; leave a 20-sec voicemail, then email "tried to reach you."
4 Day 5 Email New angle: a proof point / peer result relevant to their segment.
5 Day 8 LinkedIn Share or comment with a relevant resource (article, data point).
6 Day 11 Call + voicemail Different pain angle; voicemail naming a peer outcome.
7 Day 14 Email Pattern-interrupt: short, one provocative question tied to their world.
8 Day 18 Email Breakup email (see below).

Read the full file on GitHub · 113 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. 10d ago First seen · 113 lines · 72 tokens per session scan A 5d13fca448bc

Subscribe to this mod's changes

sequence-writing is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 1,398 once invoked, about $0.0004 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.