cold-outreach

cold-outreach is a skill for Codex from san-npm/skills-ws. It costs 81 tokens per session (7,190 once invoked), scanned A, original, MIT.

A guide to business-to-business cold outreach by email and LinkedIn, including sender authentication, message sequences, personalization, and compliance.

In plain words
What is it for?
Use it to configure SPF, DKIM, and DMARC, write outreach sequences, manage opt-outs, and follow CAN-SPAM, GDPR, and CASL requirements.
Why use it?
It helps reduce spam-folder delivery, weak responses, and legal or privacy mistakes in unsolicited outreach.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to configure SPF, DKIM, and DMARC, write outreach sequences, manage opt-outs, and follow CAN-SPAM, GDPR, and CASL requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/san-npm/skills-ws/cold-outreach
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 san-npm/skills-ws --skill cold-outreach
Clone the repo
git clone --depth 1 https://github.com/san-npm/skills-ws

Made for: 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-outreach

README.md
[![agentmods](https://agentmods.dev/badge/skills/san-npm/skills-ws/cold-outreach/github.svg)](https://agentmods.dev/skills/san-npm/skills-ws/cold-outreach)
Your own site
<a href="https://agentmods.dev/skills/san-npm/skills-ws/cold-outreach"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/cold-outreach/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-outreach

Your own site · 80×15
<a href="https://agentmods.dev/skills/san-npm/skills-ws/cold-outreach"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/cold-outreach.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 7,190 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 $0.00081 $0.07190
Opus 5.5 $0.00032 $0.02876
Sonnet 5.5 $0.00016 $0.01438
Haiku 4.5 $0.00008 $0.00719

Measured 2mo ago against content hash a831acf28c45, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cold-outreach 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 2mo 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/cold-outreach/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cold Outreach

Workflow

1. Deliverability Setup

Do this BEFORE sending a single email. Skipping this = spam folder.

DNS records (required) — publish only the ESP you actually send through. Do not copy a multi-include SPF "starter" record; each include: costs DNS lookups (SPF hard-fails at 10 lookups per RFC 7208) and an unused include both wastes a lookup and authorizes a sender you don't use.

# SPF — pick ONE example matching your ESP. Use ~all (softfail) while warming, -all once stable.
# Google Workspace:   v=spf1 include:_spf.google.com ~all
# SendGrid:           v=spf1 include:sendgrid.net ~all
# Microsoft 365:      v=spf1 include:spf.protection.outlook.com ~all
# Amazon SES:         v=spf1 include:amazonses.com ~all
# Most cold-email senders (Instantly/Smartlead) ship a dedicated domain — use the
# exact SPF/DKIM strings from THEIR setup wizard, not the strings above.

# DKIM — your ESP generates the keypair and gives you the exact TXT record + selector.
# Publish it verbatim. Prefer a 2048-bit key. Example selector:
sg._domainkey.example.com  TXT  "v=DKIM1; k=rsa; p=MIGfMA0GCSq..."   # value from ESP

# DMARC — start at p=none with reporting; tighten only after SPF+DKIM align cleanly for ~2 weeks.
_dmarc.example.com  TXT  "v=DMARC1; p=none; rua=mailto:[email protected]; fo=1"

Alignment, not strictness. DMARC passes on relaxed alignment by default (org-domain match), which is all Gmail/Yahoo require. Do not reflexively set aspf=s; adkim=s — strict mode breaks legitimate setups where the ESP signs with a subdomain or rewrites the envelope (common with shared sending domains). Leave alignment relaxed (the default) unless you control every signing surface and have a specific spoofing reason.

Verify before you send (run these; don't trust the dashboard alone):

dig +short TXT example.com                         # SPF: exactly one v=spf1 record, <10 includes
dig +short TXT sg._domainkey.example.com           # DKIM: your selector resolves to v=DKIM1 ...
dig +short TXT _dmarc.example.com                   # DMARC: v=DMARC1; p=...; rua=...
# Count SPF lookups (must stay <=10):
dig +short TXT example.com | grep -o 'include:' | wc -l
# End-to-end: send one message to a Gmail account, open "Show original" → expect
#   SPF: PASS,  DKIM: PASS,  DMARC: PASS

If you use a click/open tracking domain, host it as a CNAME on a subdomain you control (e.g. track.example.com) and confirm it isn't on a blocklist — a shared/blacklisted tracking domain tanks deliverability even when auth passes.

Read the full file on GitHub · 387 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 387 lines · 81 tokens per session scan A a831acf28c45

Subscribe to this mod's changes

cold-outreach is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 7,190 once invoked, about $0.0003 per session on Opus 5.5. 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

cold-outreach compared with skills from other repositories

cold-outreach next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cold-outreachsan-npm/skills-wsSkill41mo agoMITA81Codex
fto-triageanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A81Claude Code
legal-holdanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A68Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA49Claude Code
terms-of-servicegenspark-ai/genofficeSkill12k2d agoApache-2.0A32Claude Code, Codex
x-scorecardx-cmd/x-cmdSkill4.7k7d agoApache-2.0A57Claude Code, Codex
gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-rechtSkill1.8kyesterdayApache-2.0A69Claude Code