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 agentmods add skills/leandroz/claude-plugins/cold-emailnpx 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.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.00608 |
| Opus 5 | $0.00023 | $0.00304 |
| Sonnet 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 4d 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.
- 4d 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 (14 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 608 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…