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 icp-definitiongit 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/icp-definition)<a href="https://agentmods.dev/skills/msolecki/founder-os/icp-definition"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/icp-definition.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 | $0.00037 | $0.02218 |
| Opus 5 | $0.00018 | $0.01109 |
| Sonnet 5 | $0.00007 | $0.00444 |
| Haiku 4.5 | $0.00004 | $0.00222 |
Grade A, and why
icp-definition 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 7d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ICP Definition
An ICP that excludes nobody is a mailing list. The founder already knows they serve "businesses that need help" — that sentence has never disqualified a single bad-fit call, which is the only job an ICP has.
When to use
Before offer-design, always — an offer for nobody in particular is a service
menu. Also when the founder describes their buyer with adjectives ("ambitious",
"values quality", "gets it"), when every project is bespoke, or when a prospect
says "this is interesting" and vanishes. Run when /founder-os-init hands off
here — it is the first stop after the charter.
First-run branch
Use this branch only when /founder-os-init invokes the skill and clients/
contains no paid-client evidence. Supplied companies are examples of the
founder's preference, not clients and not proof. A first-run result is allowed
to be thin; it is not allowed to sound researched.
| Input state | Classification | Required action |
|---|---|---|
paid-client evidence |
The workspace is not evidence-empty. | Leave this branch and use the recurring evidence path from clients/. |
founder examples only |
The named examples are preference, not evidence. | Write a dated hypothesis as of YYYY-MM-DD, name the supplied named examples, mark them not evidence, and hand a queue validation proposal to the Chief of Staff. |
examples unknown |
The ICP evidence and examples are UNKNOWN. |
Write UNKNOWN rather than a segment, hand a queue validation proposal to the Chief of Staff, and do not invent examples or attributes. |
For the examples-only path, replace only offer.md ## ICP with:
## ICP
Updated: YYYY-MM-DD
Status: hypothesis — no paid-client evidence
### Who
<one-sentence hypothesis from the observable difference, or UNKNOWN>
### Trigger
UNKNOWN — no paid-client trigger supplied
### Attributes to test
- <observable difference supplied by the founder> — hypothesis, not evidence
### Not this
- <supplied named exclusion> — founder preference, not client evidence
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.
- 7d ago First seen · 196 lines · 37 tokens per session scan A 1f3c0b0c92a7
icp-definition is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 2,218 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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…