sequence-writer

sequence-writer is a skill for Claude Code from swan-gtm/gtm-skills. It costs 81 tokens per session (1,122 once invoked), scanned A, original, MIT.

A set of cold outreach messages built around a specific recent event at a company, such as a new executive, funding round, hiring increase, or buying signal. Cold outreach means contacting someone who has not requested a conversation.

In plain words
What is it for?
Use it to create a multi-step email sequence with subject lines and messages aimed at a defined outcome, such as booking a discovery call.
Why use it?
It avoids generic sales templates by grounding each message in something that actually happened at the account. It also checks that the intended contact still works there before writing.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to create a multi-step email sequence with subject lines and messages aimed at a defined outcome, such as booking a discovery call.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swan-gtm/gtm-skills/sequence-writer
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 swan-gtm/gtm-skills --skill sequence-writer
Clone the repo
git clone --depth 1 https://github.com/swan-gtm/gtm-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 sequence-writer

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

agentmods 80×15 button for sequence-writer

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/sequence-writer"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/sequence-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,122 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00081 $0.01122
Opus 5 $0.00041 $0.00561
Sonnet 5 $0.00016 $0.00224
Haiku 4.5 $0.00008 $0.00112

Measured 9d ago against content hash cead273196f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sequence-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 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.

skills/gal-tamir/sequence-writer/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write a complete cold outreach sequence grounded in a specific trigger event. Verify the contact first. Build every step around what actually happened at the account. Stop when there's nothing left worth saying.

Input

The user will provide via $ARGUMENTS:

  • Trigger event: what happened at the account (e.g. "new VP of Sales joined", "Series B closed", "hiring surge in SDR roles", "intent signal on prospecting data")
  • Contact: name and company, email, or LinkedIn URL
  • What you sell: one sentence — product and the problem it solves
  • Target outcome: what you want the sequence to achieve (e.g. "book a 20-minute discovery call")
  • Tone: [optional] — direct / conversational / formal
  • Steps: [optional] — number of steps, default is 5

If trigger event or contact is missing, ask once. If what you sell is missing, ask once. Never write the sequence before verifying the contact.

Workflow

  1. CONTACT VERIFICATION Resolve and verify the contact via Lusha before writing anything:

    • Current title and company confirmed
    • Tenure in current role
    • Verified email address
    • Flag if contact has departed — do not write sequence until user confirms new contact
    • Flag if title has changed since signal fired
  2. ACCOUNT SIGNAL CONFIRMATION Confirm the trigger event via Lusha and check for additional signals at the account:

    • Verify the primary trigger is current and accurate
    • Surface any stacked signals — additional events at the same account in the last 90 days
    • Note signal recency — older signals get less prominence in the sequence
  3. SEQUENCE ARCHITECTURE Before writing, define the arc:

    • Step 1: Lead with the trigger — specific, observed, no product pitch
    • Step 2: Connect signal to a problem your product solves — relevance, not features
    • Step 3: Social proof — a customer in a similar position who had the same problem
    • Step 4: Stacked signal or urgency — why now matters, not just why you
    • Step 5: Final close — direct ask, easy to say yes to

Read the full file on GitHub · 188 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 · 188 lines · 81 tokens per session scan A cead273196f8

Subscribe to this mod's changes

sequence-writer is a skill published in the GitHub repository swan-gtm/gtm-skills (150 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,122 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 2026-09-03.