cold-email-preflight

cold-email-preflight is a skill for Claude Code, Codex from swan-gtm/gtm-skills. It costs 50 tokens per session (557 once invoked), scanned A, original, MIT.

A pre-launch checklist for cold email campaigns covering sender authentication, address quality, message risks, sending volume, and stop conditions.

In plain words
What is it for?
Use it immediately before launch to decide whether to send or hold the campaign and define rules for pausing it.
Why use it?
It helps prevent a campaign from launching with delivery, list, copy, or volume problems that can damage sending reputation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it immediately before launch to decide whether to send or hold the campaign and define rules for pausing it.

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

Made for: Claude Code, Codex.

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 cold-email-preflight

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/cold-email-preflight"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/cold-email-preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 557 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 $0.00050 $0.00557
Opus 5 $0.00025 $0.00279
Sonnet 5 $0.00010 $0.00111
Haiku 4.5 $0.00005 $0.00056

Measured 9d ago against content hash 7d63e83e3ada, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cold-email-preflight 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/imad-badreddine/cold-email-preflight/SKILL.md · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run this in the hour before a cold email campaign goes live. It produces a launch or hold decision, and the thresholds that will stop the campaign if the first days go wrong.

The play

  1. Authentication: confirm the sending domain passes SPF, DKIM, and DMARC, and that tracking runs on a custom domain, not the tool's shared one. Any failure is an automatic hold.
  2. List quality: verify every address in the batch and drop anything the verifier is not sure about. A launch list should carry effectively zero known-bad addresses; the bounce budget is spent on the unknowable ones.
  3. Copy risk pass: first message carries no links and no attachments, reads like one person wrote it to one person, and every variable has a fallback so no prospect ever sees a naked placeholder. Vary phrasing across the sequence; identical strings at volume are a fingerprint.
  4. Volume sanity: the day-one schedule respects each mailbox's earned capacity, ramps across the week rather than front-loading Monday, and total daily volume matches what the warmed infrastructure can carry.
  5. Set the kill-switches before launch, in writing: the bounce-rate line and the placement signal that pause the campaign automatically, and who gets alerted. Deciding thresholds after the numbers arrive means deciding them emotionally.
  6. First-week watch: check bounce rate and reply rate daily per mailbox. Bounces spiking means the list lied; replies flat while opens hold means the copy missed; both healthy means scale one step.

What good looks like

  • The expert habit is checking the boring plumbing first: authentication and list hygiene kill more campaigns than bad copy ever will, yet they take ten minutes to verify.
  • The mediocre version launches full volume on day one with unverified addresses, links in message one, and no agreed stopping rule: every failure after that is improvisation.
  • A good launch is quiet: bounces near zero, no placement alerts, and the only surprise in week one is which variant of the copy wins.

Read the full file on GitHub · 36 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 · 36 lines · 50 tokens per session scan A 7d63e83e3ada

Subscribe to this mod's changes

cold-email-preflight is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 557 once invoked, about $0.0003 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.