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 tough-tongue/demo-prep-skills --skill outreach-writergit clone --depth 1 https://github.com/tough-tongue/demo-prep-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/tough-tongue/demo-prep-skills/outreach-writer)<a href="https://agentmods.dev/skills/tough-tongue/demo-prep-skills/outreach-writer"><img src="https://agentmods.dev/badge/skills/tough-tongue/demo-prep-skills/outreach-writer/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/tough-tongue/demo-prep-skills/outreach-writer"><img src="https://agentmods.dev/badge/skills/tough-tongue/demo-prep-skills/outreach-writer.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 | $0.00050 | $0.01618 |
| Opus 5 | $0.00025 | $0.00809 |
| Sonnet 5 | $0.00010 | $0.00324 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
outreach-writer 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outreach Writer
Write personalized outreach messages — cold emails, LinkedIn connection requests, pre-demo emails, and warm intro templates. Every message is grounded in research and customized to the user's product positioning.
When to Use
- User says "write an email to [name] at [company]"
- User needs a LinkedIn connection request or InMail
- User wants a pre-demo email to send before a scheduled call
- User needs a warm intro request to send through a mutual connection
- User asks to write any prospecting or sales communication
Required Inputs
Ask the user for:
Prospect: [Name, title, company]
Outreach Type: [Cold email / LinkedIn connection / Pre-demo email / Warm intro request]
Context: [Why are you reaching out? Any shared connection or trigger event?]
If the user just says "write an email to Sarah at Acme," research first, then ask which type of outreach they need.
Process
1. Load Context
Read company-profile.md for the user's product positioning, differentiators, and background.
2. Research the Prospect
If not already done, use the research-prospect process to gather company and contact intelligence. You need at minimum:
- What the prospect's company does
- The contact's role and background
- A personalization hook
3. Generate the Message
Use the appropriate template based on outreach type. See Email Best Practices for style rules.
Output Formats
Cold Email
Subject: [Short, specific, curiosity-driving — no clickbait]
Hi [First Name],
[HOOK — 1 sentence. Reference something specific: a recent post, a trigger event, a shared connection, or a specific observation about their business.]
[BRIDGE — 1-2 sentences. Connect their situation to the problem you solve. Don't pitch features — describe the outcome.]
[CTA — 1 sentence. One clear ask: a 15-minute call, permission to send a demo, or a yes/no question.]
[Sign-off],
[User Name]
[Title, Company]
Rules:
- Under 100 words in the body
- No more than 3 sentences before the CTA
- The subject line should make them want to open, not summarize the email
- Never lead with "I" — lead with them
What ships with it
1 file 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 · 219 lines · 50 tokens per session scan A 91d2a6805ba5
outreach-writer is a skill published in the GitHub repository tough-tongue/demo-prep-skills (5 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,618 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 2026-08-31.
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…