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 schub-tech/llm-ideation-wiki --skill founder-profilegit clone --depth 1 https://github.com/schub-tech/llm-ideation-wikiWrote 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/schub-tech/llm-ideation-wiki/founder-profile)<a href="https://agentmods.dev/skills/schub-tech/llm-ideation-wiki/founder-profile"><img src="https://agentmods.dev/badge/skills/schub-tech/llm-ideation-wiki/founder-profile/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/schub-tech/llm-ideation-wiki/founder-profile"><img src="https://agentmods.dev/badge/skills/schub-tech/llm-ideation-wiki/founder-profile.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 | $0.00082 | $0.00947 |
| Opus 5 | $0.00041 | $0.00474 |
| Sonnet 5 | $0.00016 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00095 |
Grade A, and why
founder-profile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Capture the founder profile that every later idea will be measured against. One Notion page, six questions, then a tension check.
Read first.
hot.md,wiki/index.md,notion.config.json.- If
wiki/founderalready exists innotion.config.json, fetch it withscripts/notion_wiki.py get wiki/founderand offer to update rather than overwrite.
Ask one question at a time. Wait for the answer before moving on — multi-question dumps let the user dodge the hard one. Reflect each answer back in one short line before asking the next, so the user can correct drift early.
Ask these six, in order:
- Team shape — solo founder, small team (≤10), or large organization?
- End game — fast exit (growth play), IPO (valuation play), or hold-and-run (profit/lifestyle play)?
- Financial success — what's the number? Net to the founder, total enterprise value, or annual income — be specific about which.
- Timeframe — by when does (3) need to be true?
- Investment willingness — how much of your own time (hours/week, years) and your own money (€/$ ceiling) are you willing to commit before the idea has to pay for itself?
- Risk tolerance — what probability of going to zero are you comfortable with? Frame as a number, not "I'm okay with risk."
If the user gives a vague answer (e.g. "a lot", "comfortable", "soon"), ask one clarifying follow-up to pin a number or category. Do not move on without one.
Reality check — tensions in the answers only.
After all six are captured, scan the answers against each other and surface any tensions in 3–6 bullets. Examples of the kind of tension worth flagging:
- Solo founder + IPO end game + short timeframe.
- High financial target + low capital willingness + low risk tolerance.
- Lifestyle/profit end game + fast-exit-sized number.
- Timeframe shorter than typical category cycle (e.g. 2 years to a regulated-market IPO).
Do not bring in market or idea-specific facts — this is a self-consistency check on the stated answers. If there are no tensions, say so in one line and move on. No manufactured objections, no padding.
If the user wants to revise an answer in light of the tensions, update before writing.
Write to Notion.
- Create the page if missing:
scripts/notion_wiki.py create wiki/founder --parent wiki/ --title "Founder" --emoji 🎯 --file <markdown-file> - If it already exists, update it:
scripts/notion_wiki.py update wiki/founder <markdown-file>
Page body, in this order:
- One-line lede: who the founder is and what shape company they want.
- Ambition table or bullets: team shape, end game, financial target (with which metric), timeframe.
- Willing to invest: time and money ceilings.
- Risk tolerance: stated probability-of-zero comfort.
- Tensions (only if any were surfaced): one bullet per tension, plain and direct.
- Last updated: today's date.
Mark every stated answer as ^[user-claim]. Mark tensions as ^[inferred]. Do not invent numbers the user did not give — if they refused to pin one, write "not pinned" rather than guessing.
Finish.
- Run the ritual (
AGENTS.md§ Mechanics). - Tell the user the page is at
wiki/founderin Notion and that the next step is/new-idea.
Rules.
- One page only:
wiki/founder. Never per-idea. - Do not check the profile against any specific idea here. Idea-vs-profile fit is the job of later skills (
new-idea,grill-me,wiki-lint, idea overview synthesis) once an idea has enough surface area to test.
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.
- 9d ago First seen · 66 lines · 82 tokens per session scan A 8e5deb4056cd
founder-profile is a skill published in the GitHub repository schub-tech/llm-ideation-wiki (11 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 947 once invoked, about $0.0004 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
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
box
Box manages cloud files, sharing, search, and metadata.
obsidian
Read, search, create, and edit notes in the Obsidian vault.