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 AgentlyLabs/founder-skills --skill cold-emailgit clone --depth 1 https://github.com/AgentlyLabs/founder-skillsWrote 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/agentlylabs/founder-skills/cold-email)<a href="https://agentmods.dev/skills/agentlylabs/founder-skills/cold-email"><img src="https://agentmods.dev/badge/skills/agentlylabs/founder-skills/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/agentlylabs/founder-skills/cold-email"><img src="https://agentmods.dev/badge/skills/agentlylabs/founder-skills/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 | $0.00236 | $0.01913 |
| Opus 5 | $0.00118 | $0.00957 |
| Sonnet 5 | $0.00047 | $0.00383 |
| Haiku 4.5 | $0.00024 | $0.00191 |
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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Outbound That Reaches and Gets Replies
What decides the outcome
Three independent systems have to succeed, in this order:
- Delivery. An unauthenticated message never gets read, however good it is. This is deterministic, checkable, and the most common silent failure.
- Legality. What you must include, and whether you may send at all, depends on where the recipient is. The US, EU/UK, and Canada have materially different regimes.
- The reply. Copy craft, which is where nearly all published advice lives and where the least of it is verifiable.
Most outbound fails at (1) while the sender rewrites (3). So diagnose in order, and never skip Step 1 because the copy looks like the interesting problem.
The discipline in this skill: every recommendation names its mechanism, and metrics that
cannot be measured are called out rather than reported. Open rates in particular are
close to meaningless now — see references/deliverability.md.
Scope
This is for targeted outreach at low volume: a researched list where you can state, per recipient, why you emailed that person. That is both the legally defensible posture and the one that actually works — reply rate collapses as list size grows, because the specific reason for the email is what earns the reply.
If the user wants high-volume untargeted blasting, say plainly that it will burn the sending domain, and that the domain reputation damage is slow to reverse. Then help them do the targeted version.
Step 1 — Audit the sending domain before writing anything
Run this first, every time, even if the user only asked for copy help:
python3 scripts/check_domain.py example.com
It resolves SPF, DKIM (probing common selectors), DMARC, MX, MTA-STS and TLS-RPT, then
reports each as PASS / WARN / FAIL with the specific fix. Add --json for machine output,
--selectors s1,s2 to probe custom DKIM selectors.
Interpret the result against references/deliverability.md, which has the actual provider
requirements — including the distinction almost everyone gets wrong: Google requires SPF
or DKIM from all senders, but SPF and DKIM and DMARC with alignment from bulk
senders (5,000+ messages/day to Gmail). Know which set applies before you tell the user
what is mandatory.
What ships with it
7 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.
- 12d ago First seen · 153 lines · 0 tokens per session scan A c6a018660c22
cold-email is a skill published in the GitHub repository AgentlyLabs/founder-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 236 tokens to every session and 1,913 once invoked, about $0.0012 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.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…