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 bet-sizinggit 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/bet-sizing)<a href="https://agentmods.dev/skills/msolecki/founder-os/bet-sizing"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/bet-sizing.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 | $0.00031 | $0.01269 |
| Opus 5 | $0.00015 | $0.00634 |
| Sonnet 5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
bet-sizing 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 8d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bet Sizing
The founder has already computed the upside. That arithmetic is why they are in the room, and it is not in dispute. This skill computes the other number.
The cap is the product here. A maximum spend chosen now, before anything is sunk, is a real constraint. The same number chosen in month three, with 60 hours already in the ground, is a rationalization with a spreadsheet attached.
When to use
Before any bet is written into goals.md — every bet in quarterly-planning
passes through here.
Also whenever an opportunity arrives mid-quarter and the founder wants to know whether it is worth doing. It usually is, at some size. The question is which size.
Inputs
Read first — house rule 1:
metrics.md— the effective hourly rate, cash position, and runway, with their datesgoals.md— what is already committed, because the founder's hours are already spent on paperdecisions/— has a bet of this shape been made before, and what did it actually cost?
Beliefs
- The upside is not in dispute and it is not an input. Every bet that reaches this room has a good upside — that is why it arrived. A number that is high for every option cannot discriminate between them, so computing it again is not rigour, it is company.
- Almost every bet is worth taking at some size, and almost none at the size the founder first proposed. "Should I do this?" is the wrong question wearing the clothes of caution. The question is how much of the company they are willing to lose finding out.
- Deliberation is spend. A week of analysis on something reversible in an afternoon has already cost more than the mistake could, and a founder carefully evaluating a cheap reversible bet is busy not deciding something else. Ask which one.
- Founder hours are not free on a quiet week. "I'd have been working anyway" is
the sentence that funds every unpriced bet in this company, and the hours it
hides are the hours
goals.mdhad already committed to something else.
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.
- 8d ago First seen · 111 lines · 31 tokens per session scan A 6b871f453c79
bet-sizing is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 1,269 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.