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 jaredlangleycc/nightshift-os --skill outreach-draftergit clone --depth 1 https://github.com/jaredlangleycc/nightshift-osWrote 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/jaredlangleycc/nightshift-os/outreach-drafter)<a href="https://agentmods.dev/skills/jaredlangleycc/nightshift-os/outreach-drafter"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/outreach-drafter/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/jaredlangleycc/nightshift-os/outreach-drafter"><img src="https://agentmods.dev/badge/skills/jaredlangleycc/nightshift-os/outreach-drafter.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 | $0.00107 | $0.01940 |
| Opus 5 | $0.00053 | $0.00970 |
| Sonnet 5 | $0.00021 | $0.00388 |
| Haiku 4.5 | $0.00011 | $0.00194 |
Grade C, and why
outreach-drafter scanned grade C with 1 finding 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 10d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Don't refuse to draft. Just surface the mismatch. The user might have a reason. How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outreach Drafter
First-touch outreach. One-off messages to a specific prospect, LinkedIn connection requests, intro emails, DMs, "noticed your post" replies. Draft style matches the user's voice and the situation, never generic.
When this skill triggers
- "Write a LinkedIn DM to [name]"
- "Draft an outreach email to [prospect]"
- "What should I say to [contact]"
- "Connection request for [person]"
- "Cold email this prospect"
- "Draft an intro to [contact]"
- "Reach out to [company] about [reason]"
NOT for: full sequences (use cold-email), follow-ups (use follow-up-tracker), warm intros via mutual (different pattern, use this skill but flag as warm intro).
The 4-question intake
Before drafting, ask in this order (one at a time, coach-mode):
Q1: Who is the prospect, specifically?
Need:
- Name
- Role
- Company (with 1-line description if not well-known)
- Why they're worth reaching out to (specific signal, not "they look interesting")
If the user can't answer the last one, push back: "What made you pick them? If you can't name it, the message won't either."
Q2: What's the connecting thread?
A specific reason this message isn't generic. Options:
- Shared connection (named)
- Their recent post/podcast/article (named)
- Their company news (acquired, funding, hire, launch)
- Mutual experience (same conference, school, previous company)
- Direct relevance to a problem they've signaled
No thread = no message. Ask the user to find one or skip the prospect.
Q3: What's the ask?
One ask. Not three.
Options:
- Connect (no agenda, build network)
- 15-min intro call
- Reply to a specific question
- Reaction to something you sent (resource, post)
- Intro to someone in their network
If the user says "all of the above," push back. One ask. The smallest one that moves the relationship forward.
Q4: What's their likely first thought?
Imagine the prospect reading the message. What's the 2-second reaction? "Who is this?" "Another pitch?" "Oh, that's interesting." The message must address this.
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.
- 10d ago First seen · 263 lines · 107 tokens per session scan C 8b15d8dc594a
outreach-drafter is a skill published in the GitHub repository jaredlangleycc/nightshift-os (3 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,940 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Brand Guidelines Generator
Create and maintain brand style guides for consistent visual identity.
web-vid
Turn a web app or marketing site into a recreated (not screen-recorded) Remotion promo video — pixel-faithful to the site's own design system, choreographed clicks/scrolls/zooms, rendered to MP4. Use when the user asks for a product demo video, a promo/teaser for LinkedIn or social, an "walkthrough video" of their…
pitchdocs
Generate marketing-quality repository documentation from codebase analysis. Scans 10 signal categories, extracts features with file-level evidence, and produces README, CHANGELOG, ROADMAP, and 15+ more docs. Zero runtime dependencies. For AI context file management, see ContextDocs.
demo-video-factory
Generate a custom 26s product-demo video from any SaaS URL — brand-matched scenes, a recreated product-UI "wow" scene, real screenshots, and a soundtrack. Use whenever the user wants a demo, promo, launch, or marketing video for a website or product.
brand
Brand context management for marketing sessions with continuity across conversations.
liking-factor-engineer
Analyze and engineer liking to increase rapport, persuasion, and compliance in marketing, sales, and communication contexts. Use this skill when the user wants to improve how much an audience likes them, their brand, or their message — including writing sales copy, designing onboarding flows, crafting brand voice…