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/msolecki/founder-os/outreach-draftnpx skills add msolecki/founder-os --skill outreach-draftgit clone --depth 1 https://github.com/msolecki/founder-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/msolecki/founder-os/outreach-draft)<a href="https://agentmods.dev/skills/msolecki/founder-os/outreach-draft"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/outreach-draft.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 | $0.00038 | $0.02797 |
| Opus 5 | $0.00019 | $0.01399 |
| Sonnet 5 | $0.00008 | $0.00559 |
| Haiku 4.5 | $0.00004 | $0.00280 |
Grade A, and why
outreach-draft 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 5d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Outreach Draft
The founder's outreach fails for one reason: it is about the founder. It opens with who they are, describes what they do, and asks the prospect to work out whether any of it is relevant to them. The prospect does not do that work. They do not do it for anyone.
The second reason is "just checking in" — a message that asks the recipient to invent a reason for the conversation on the founder's behalf. Its reply rate is why the founder believes their market is cold. The market is fine. The message was empty.
When to use
When pipeline-review produced a next action that is an outreach. When a deal
has gone quiet and the founder wants to follow up. When the founder is about to
send something at 11pm because a prospect crossed their mind.
Inputs
Read first, in order — house rule 1:
-
pipeline.md— this prospect: what has already been sent, when, and what they said. Repeating an angle they already ignored is worse than silence. -
offer.md— the ICP and the trigger. If this prospect does not fit the ICP, say so before drafting a word. -
voice.md— read this before you write a sentence, not after.## Samplesis the founder's actual sent mail;## Tellsis what makes it recognisably theirs;## Neveris the phrase list that gets a message deleted on sight;## Registersays how cold outreach differs from a mail to a client of two years — this is the coldest register in the file and the least forgiving of a wrong one.If
## Samplesis empty, say so out loud in the handoff — "no voice samples on record; this is written in a default register and will read like it" — and hand the foundervoice-capture(Brand Editor). Drafting silently on an empty voice file is how a message that is correct about the prospect still reads like every other automated email in the inbox. Do not reconstruct a voice fromcontent.md, from published posts, or from the founder's description of themselves. -
network.md— is this person already the Network Manager's? If there is no deal, they are, and cold outreach against a warm relationship burns it.
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.
- 5d ago First seen · 217 lines · 38 tokens per session scan A 758315450239
outreach-draft is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 2,797 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 2026-08-31.
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…