email-skills CLAUDE.md

email-skills CLAUDE.md is an instructions file for coding agents from sendx/email-skills. It costs 555 tokens per session, scanned A, original, MIT.

Repository instructions for a collection of AI-agent skills for email marketing. They explain the folder layout, required SKILL.md format, categories, and how the skills refer to one another.

In plain words
What is it for?
Use them when creating or editing email-marketing skills in this repository. They cover tasks such as deliverability, compliance, campaigns, content, growth, analytics, and email-platform operations.
Why use it?
They give contributors a shared structure for adding or maintaining skills without guessing where files belong or what metadata they need. They also explain the difference between SendX, an email marketing platform, and SendPost, an email infrastructure API.

Instructions file

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.

agentmods
npx agentmods add instructions/sendx/email-skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/sendx/email-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 email-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sendx/email-skills/claude-md.svg)](https://agentmods.dev/instructions/sendx/email-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sendx/email-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/sendx/email-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 555 This file is loaded in full into every session.
When invoked 555 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00555 $0.00555
Opus 5 $0.00278 $0.00278
Sonnet 5 $0.00111 $0.00111
Haiku 4.5 $0.00056 $0.00056

Measured 5d ago against content hash 8906e1d47431, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

email-skills CLAUDE.md 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Email Marketing Skills

A collection of AI agent skills for email marketing, built by SendX and SendPost.

Repo structure

  • skills/<skill-name>/SKILL.md — each skill is a standalone markdown file
  • All skills are flat: skills/<skill-name>/SKILL.md
  • Categories are organizational labels in the README, not filesystem directories

Skill format

Every SKILL.md has YAML frontmatter:

---
name: skill-name
description: "One sentence description"
category: deliverability | compliance | campaign | content | growth | analytics | esp-ops
---

Followed by the skill instructions in markdown.

How skills work

Each skill gives the agent specialized knowledge for one email marketing task. Skills reference each other by name (e.g., "see the smart-segmentation skill when targeting needs work").

The email-deliverability-expert-skill includes a references/ folder with supplementary docs: provider-specific tactics, shared pool management, and a warmup playbook.

Key context

  • SendX = email marketing platform (campaigns, automation, segmentation, analytics)
  • SendPost = email infrastructure API (IP management, bounce processing, deliverability monitoring)
  • Target audience for skills = non-technical email marketers
  • Skills should use plain language, avoid jargon, include real benchmarks and thresholds
  • Every claim should be actionable: "your bounce rate is above 2%" beats "your bounce rate is high"

Available skills

  • ab-testing — Email A/B testing
  • api-campaign-builder — SendX API campaign management
  • campaign-strategy — Campaign type selection
  • compliance-navigator — Email privacy law compliance
  • email-analytics — Metric interpretation and actions
  • email-copywriting — Subject lines, preview text, body copy
  • email-deliverability-expert-skill — Deliverability audit, diagnosis, and fixes (has references/)
  • esp-hardbounce-unlock — Hard bounce unlock evaluation
  • esp-malicious-behavior — Malicious sender investigation
  • industry-playbooks — Vertical-specific email strategies
  • list-growth-engine — List building with popups, forms, lead magnets
  • smart-segmentation — List segmentation and targeting
  • workflow-automation — Automated email sequences

Read the full file on GitHub · 60 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. 5d ago First seen · 60 lines · 555 tokens per session scan A 8906e1d47431

Subscribe to this mod's changes

email-skills CLAUDE.md is an instructions file published in the GitHub repository sendx/email-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 555 tokens to every session, about $0.0028 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 instructions, from other repositories

mcp-eu-compliance AGENTS.md

AGENTS.md instructions for matematicsolutions/mcp-eu-compliance, covering agents.md - mcp-eu-compliance, project purpose, matematic context (hard constraints), mcp tools (tools contract) and build and test.

matematicsolutions/mcp-eu-compliance · 1,322 tokens

sign-cli AGENTS.md

AGENTS.md instructions for DrBaher/sign-cli, covering agents, output contract, exit codes, discovery and the signing asymmetry.

DrBaher/sign-cli · 1,179 tokens

uae-regulations-registry AGENTS.md

AGENTS.md instructions for nshield-security/uae-regulations-registry, covering agents.md — instructions for ai agents, what this repo contains, preferred entry points, json schema (data/regulations.json) and stable urls.

nshield-security/uae-regulations-registry · 835 tokens

kiwi-paper GEMINI.md

Instructions for hletrd/kiwi-paper, covering kiwi-paper — gemini cli instructions, 사용법, 4단계 파이프라인, 지원 문서 유형 (12종) and 핵심 규칙.

hletrd/kiwi-paper · 421 tokens

outlookctl CLAUDE.md

Claude Code instructions for gmickel/outlookctl, covering claude.md - development guide, project overview, key points, architecture and module responsibilities.

gmickel/outlookctl · 1,620 tokens

docker-compose-audit CLAUDE.md

Claude Code instructions for UnbearableDev/docker-compose-audit, a project described as: MCP server that audits docker-compose.yml for security misconfigurations. 25 checks across 9 categories. Pay-per-event on Apify Store.

UnbearableDev/docker-compose-audit · 5 tokens