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/alebgl77/claude-inc/draft-outreachnpx skills add alebgl77/claude-inc --skill draft-outreachgit clone --depth 1 https://github.com/alebgl77/claude-incWrote 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/alebgl77/claude-inc/draft-outreach)<a href="https://agentmods.dev/skills/alebgl77/claude-inc/draft-outreach"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/draft-outreach.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 5.1 | $0.00069 | $0.00730 |
| Opus 5 | $0.00034 | $0.00365 |
| Sonnet 5 | $0.00014 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
draft-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 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Outreach — Cold Emailer
"Earn the reply, don't trick it."
When to use
- "Write a cold email to {prospect}"
- "Draft outreach for this account"
- "Follow up, they never answered"
- Right after
account-research— never write outreach to a stranger you haven't researched - LinkedIn DMs, X DMs and short-form intros included
Workflow
- Load the account brief (or run a quick research pass if none exists — no brief, no outreach).
- Pick the angle: one observed signal → one pain → one credible promise. One. Multi-pain emails read like spam.
- Draft the first touch: ≤ 90 words. Line 1 proves you did homework (specific, non-creepy). Line 2-3 connect pain → outcome with proof. Close with a low-friction CTA (question or 15-min ask), never "let me know your availability for a quick sync".
- Write 3 subject lines: 2-4 words, lowercase-friendly, zero clickbait. No "Re:", no fake forwards, ever.
- Build the follow-up ladder: +3 days (new value: insight/resource), +7 days (different angle or social proof), +14 days (graceful breakup that leaves the door open). Each ≤ 60 words, none saying "just bumping this".
- Personal-ify: adapt to the user's voice profile if one exists (
voice-builderoutput); default to plain, human, contraction-friendly prose. - Compliance pass: no false claims, honour opt-outs, one-click identifiable sender. Flag anything Legal should see.
Output format
## Outreach kit — {prospect}
Angle: {signal} → {pain} → {promise}
**Subject options**: 1. ... 2. ... 3. ...
**Email 1 (day 0, ≤90w)**: ...
**Email 2 (day 3, ≤60w)**: ...
**Email 3 (day 7, ≤60w)**: ...
**Email 4 (day 14, breakup)**: ...
**DM variant (≤300 chars)**: ...
Send window: {day/time + rationale}
Quality bar
- First line is specific to THIS prospect (passes the "could this be sent to anyone else?" test — answer must be no)
- ≤ 90 words for touch 1; zero jargon; reads aloud naturally
- Exactly one CTA per message
- No deceptive subjects, no fake familiarity, no guilt-tripping follow-ups
- Sequence provides new value at every touch
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 · 55 lines · 69 tokens per session scan A e94a7bbaa1b8
draft-outreach is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed 3d ago), licensed MIT. It adds 69 tokens to every session and 730 once invoked, about $0.0003 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
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
edge-tts
Text-to-speech conversion using uvx edge-tts for generating audio from text. Use when (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS…
cn-stats
中国国家统计局公开数据查询技能,当用户想查询经济、CPI、GDP、人口、房价指数等数据时触发。.
mcp-deepwiki
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
tianqi
查询中国地区的天气预报,支持15天及逐小时预报、各种生活指数.
maishou
商品价格全网对比技能,获取商品在淘宝(Taobao)、天猫(TMall)、京东(JD.com)、拼多多(PinDuoDuo)、抖音(Douyin)、快手(KaiShou)的最优价格、优惠券,当用户想购物或者获取优惠信息时使用。Get the best price, coupons for goods on Chinese e-commerce platforms, compare product prices, and use when users want to shop or get discount information.