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 leandroz/claude-plugins --skill cold-emailgit clone --depth 1 https://github.com/leandroz/claude-pluginsWrote 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/leandroz/claude-plugins/cold-email)<a href="https://agentmods.dev/skills/leandroz/claude-plugins/cold-email"><img src="https://agentmods.dev/badge/skills/leandroz/claude-plugins/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/leandroz/claude-plugins/cold-email"><img src="https://agentmods.dev/badge/skills/leandroz/claude-plugins/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 | $0.00045 | $0.00608 |
| Opus 5.5 | $0.00018 | $0.00243 |
| Sonnet 5.5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold email
A cold email is an invitation to a trade. The recipient replies when the trade excites them and ignores it when it doesn't. No subject-line trick, length optimization, or warm intro rescues a weak trade, and a strong trade survives clumsy writing. So most of the work happens before any drafting: find the real win-win.
Find the trade
Three things have to be clear before writing — who the user is emailing, what they want, and what they can offer that makes saying yes worthwhile. The third is where people stall. Dig for it rather than accepting a vague answer.
Ground it in what the recipient actually values, not what the user assumes they value. What are they working on right now? What have they said publicly that they need help with? Many influential people state this outright on their site or feed. When the user can't answer, research beats guessing.
Then state the trade plainly — what each side gets — and check with the user that both halves are genuinely appealing. A shaky trade is a signal to go back to the trade, not to write more persuasively.
Draft
The body — everything between the greeting and the sign-off — stays under 150 words. This is the one hard constraint. Influential people scan in 15–30 seconds, and every word past the point where they get it costs reply probability. If the trade needs more than 150 words to explain, it isn't sharp enough yet.
Four principles, woven together rather than stacked as separate paragraphs:
Competency — compressed proof they should keep reading: a known network, a hard number, a mutual connection who suggested the intro. Not a resume.
The ask — what the user wants and why it's worth the recipient's time, tied to something they're actively working on. Concrete beats open-ended: a specific thing to look at, a specific amount of time.
Transparent self-interest — why the user wants this and how it fits their trajectory. Hiding the motive reads as untrustworthy; pretending to pure altruism reads worse.
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.
- 2mo ago First seen · 39 lines · 45 tokens per session scan A cd8fedb994de
cold-email is a skill published in the GitHub repository leandroz/claude-plugins (15 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 608 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…