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 shawnpang/startup-founder-skills --skill cold-outreachgit clone --depth 1 https://github.com/shawnpang/startup-founder-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/shawnpang/startup-founder-skills/cold-outreach)<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/cold-outreach"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/cold-outreach/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/shawnpang/startup-founder-skills/cold-outreach"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/cold-outreach.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 | $0.00053 | $0.01638 |
| Opus 5 | $0.00026 | $0.00819 |
| Sonnet 5 | $0.00011 | $0.00328 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
cold-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cold-outreach — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Outreach
When to Use
Activate when a founder needs to write cold emails or LinkedIn messages to prospects, potential customers, investors, or strategic contacts. Also use when the user says "nobody replies to my emails," "how do I reach out to X," "write me a cold email," or "help with outbound."
Context Required
From startup-context or the user:
- Target prospect — Name, role, company, and why them specifically
- Research signals — Recent news (funding, launches, hires), LinkedIn activity, company growth data, or role/industry context
- Sender positioning — Who you are, what you offer, your unique credibility
- Platform — Email, LinkedIn, or both
- Batch size — Single prospect or multi-prospect campaign
Work with whatever the user provides. A strong research signal and clear value prop is enough to draft. Note what would strengthen the message but do not block on missing inputs.
Workflow
- Gather context — Read startup-context if available. Ask for missing info on prospect, value prop, and proof points.
- Research the prospect — Conduct web searches for recent signals. The core principle: 10 minutes of research transforms a cold message into a warm one. Rank signals by strength:
- Tier 1 (strongest): Recent news — funding rounds, product launches, key hires
- Tier 2: LinkedIn activity — posts, comments, job changes
- Tier 3: Company growth signals — hiring trends, tech stack changes
- Tier 4 (weakest): Role/industry awareness only
- Assign personalization tier — Based on research signals found:
- Tier 1 (custom): Named signals across multiple research sources — fully personalized message
- Tier 2 (templated + personalized): Company info and role context — template with personalized elements
- Tier 3 (volume template): No signals found — use volume approach with strong value prop
- Select mode based on scope:
- Quick: Single connection request + follow-up for one prospect
- Standard: Four-touch sequence for a prospect (default)
- Deep: Multi-prospect system with A/B variant messages
- Draft the sequence — Write messages following the structure and rules below.
- Self-critique pass — Before delivering, validate that personalization connects to the problem. If you remove the personalized opening and the message still makes sense, the personalization is not working. Rewrite.
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 · 117 lines · 53 tokens per session scan A cceed6b216ca
cold-outreach is a skill published in the GitHub repository shawnpang/startup-founder-skills (321 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 1,638 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
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…