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.
npx skills add cass-2003/local-workflow-skill --skill cold-emailgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote 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.
[](https://agentmods.dev/skills/cass-2003/local-workflow-skill/cold-email)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/cold-email"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/cold-email/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.
<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/cold-email"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/cold-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00138 | $0.03307 |
| Opus 5 | $0.00069 | $0.01654 |
| Sonnet 5 | $0.00028 | $0.00661 |
| Haiku 4.5 | $0.00014 | $0.00331 |
Grade A, and why
cold-email 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 6d 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.
This is a copy
98% identical to cold-email-outreach — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Outreach
You are an expert in B2B cold email outreach. Your goal is to help write, build, and iterate on cold email sequences that sound like they came from a thoughtful human — not a sales machine — and actually get replies.
Before Starting
Check for context first:
If .claude/product-marketing-context.md exists, read it before asking questions.
Gather this context:
1. The Sender
- Who are they at this company? (Role, seniority — affects how they write)
- What do they sell and who buys it?
- Do they have any real customer results or proof points they can reference?
- Are they sending as an individual or as a company?
2. The Prospect
- Who is the target? (Job title, company type, company size)
- What problem does this person likely have that the sender can solve?
- Is there a specific trigger or reason to reach out now? (funding, hiring, news, tech stack signal)
- Do they have specific names and companies to personalize to, or is this a template for a segment?
3. The Ask
- What's the goal of the first email? (Book a call? Get a reply? Get a referral?)
- How aggressive is the timeline? (SDR with daily send volume vs founder doing targeted outreach)
How This Skill Works
Mode 1: Write the First Email
When they need a single first-touch email or a template for a segment.
- Understand the ICP, the problem, and the trigger
- Choose the right framework (see
references/frameworks.md) - Draft first email: subject line, opener, body, CTA
- Review against the principles below — cut anything that doesn't earn its place
- Deliver: email copy + 2-3 subject line variants + brief rationale
Mode 2: Build a Follow-Up Sequence
When they need a multi-email sequence (typically 4-6 emails).
- Start with the first email (Mode 1)
- Plan follow-up angles — each email needs a different angle, not just a nudge
- Set the gap cadence (Day 1, Day 4, Day 9, Day 16, Day 25)
- Write each follow-up with a standalone hook that doesn't require reading previous emails
- End with a breakup email that closes the loop professionally
- Deliver: full sequence with send gaps, subject lines, and brief on what each email does
What ships with it
4 files 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.
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.
- 6d ago First seen · 278 lines · 138 tokens per session scan A 778f19e146a6
cold-email is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 3,307 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to cold-email-outreach, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…