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 assimovt/productskills --skill bet-sizinggit clone --depth 1 https://github.com/assimovt/productskillsWrote 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/assimovt/productskills/bet-sizing)<a href="https://agentmods.dev/skills/assimovt/productskills/bet-sizing"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/bet-sizing/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/assimovt/productskills/bet-sizing"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/bet-sizing.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 | $0.00056 | $0.00849 |
| Opus 5 | $0.00028 | $0.00425 |
| Sonnet 5 | $0.00011 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
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 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Size product bets by separating reversible from irreversible decisions and shaping work to fit an appetite. Most product bets are Type 2 decisions — reversible, low-cost to try, high-cost to deliberate. Move fast on those. Save deliberation for Type 1 decisions that are hard to undo.
Type 1 vs Type 2 Decisions (Bezos)
Type 1 (Irreversible): One-way doors. Hard to undo once committed.
- Choosing a core technology/platform
- Pricing model changes that affect existing customers
- Killing a product line
- Public commitments (partnerships, integrations)
Type 2 (Reversible): Two-way doors. Easy to undo or iterate.
- Most new features (can ship, measure, remove)
- UI/UX changes (can A/B test or revert)
- Internal tooling decisions
- Most API additions (harder to remove, but additive is safer)
Rule: Use lightweight process for Type 2. Use deliberate process for Type 1. Most product teams over-process Type 2 decisions and under-process Type 1 decisions.
Shape Up Pitch Format
When proposing a bet, structure it as a Shape Up pitch:
1. Problem
A specific story showing real pain. Not an abstract need — a concrete situation with a real user.
"When a PM finishes a customer interview, they spend 45 minutes transcribing notes into a PRD. By the time they're done, the emotional context is gone and the PRD reads like a requirements list."
2. Appetite
How much time is this worth? Not how long it will take — how much you're willing to invest.
- Small bet: 1-2 weeks
- Medium bet: 3-4 weeks
- Large bet: 6 weeks (maximum for Shape Up)
If you can't fit the solution in the appetite, reshape or kill it.
3. Solution
Breadboard-level, not pixel-perfect. Show the key interactions and flows without getting into visual design. Fat-marker sketches, flow diagrams, or written walkthroughs.
4. Rabbit Holes
Known risks and unknowns that could blow up the timeline. For each: what's the risk and how will you mitigate it?
5. No-Gos
What's explicitly excluded. This is as important as what's included — it prevents scope creep during execution.
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 · 78 lines · 56 tokens per session scan A 66375c7efceb
bet-sizing is a skill published in the GitHub repository assimovt/productskills (68 stars, last pushed 6mo ago), licensed MIT. It adds 56 tokens to every session and 849 once invoked, about $0.0003 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
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…
execute-fleet
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…