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 msolecki/founder-os --skill follow-up-sweepgit 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/follow-up-sweep)<a href="https://agentmods.dev/skills/msolecki/founder-os/follow-up-sweep"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/follow-up-sweep/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/msolecki/founder-os/follow-up-sweep"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/follow-up-sweep.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 | $0.00039 | $0.02776 |
| Opus 5 | $0.00019 | $0.01388 |
| Sonnet 5 | $0.00008 | $0.00555 |
| Haiku 4.5 | $0.00004 | $0.00278 |
Grade A, and why
follow-up-sweep 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 11d 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow-up Sweep
"Just checking in" is a request for the recipient to invent a reason for the conversation on the founder's behalf. Nobody does that work. The founder reads the silence as a cold network and concludes their relationships have decayed.
The network is fine. The message was empty.
This sweep finds everyone past their interval and gives each one something real — given before anything is asked. If there is nothing real to give, the sweep's answer for that person is: not this week.
When to use
Weekly. Fired by the local scheduler after setup-cadences; otherwise run
follow-up-sweep by hand. Also when the
quarter's pipeline is thin and cold outreach is being proposed before the warm
list has been touched.
Inputs
Read first, in order — house rule 1:
-
network.md## Map— thedaysandwhat they needcolumns. If the map is stale or missing, runrelationship-mapfirst; a sweep against an unknown list is a mail merge. -
pipeline.md— anyone with a live deal is excluded. They are the Pipeline Coach's this week. -
clients/— what was actually delivered for the past clients on this list. The result of that work is the best reconnect reason available and it is free. -
content.md— anything published that answers a question a specific person on this list once asked -
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 writing to someone the founder has not spoken to in a year differs from writing to a client of two years. This is the register the founder gets wrong most reliably: long silence reads to them as distance to be apologised for, and the apology is the first sentence that makes the message about them.If
## Samplesis empty, say so out loud in the handoff — "no voice samples on record; these are 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 right about the person still arrives sounding like a mail merge, which is the exact thing this sweep exists to prevent — and the recipient will blame the founder, not the draft. Do not reconstruct a voice fromcontent.md, from published posts, or from the founder's description of themselves.content.mdis on this list for reconnect reasons; published writing is a different register performed for strangers, and it is not evidence of how this founder writes to someone who knows 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.
- 11d ago First seen · 216 lines · 39 tokens per session scan A 2ad123cb1d91
follow-up-sweep is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 2,776 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…