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 product-on-purpose/pm-skills --skill tool-foundation-sprint-founding-hypothesisgit clone --depth 1 https://github.com/product-on-purpose/pm-skillsWrote 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/product-on-purpose/pm-skills/tool-foundation-sprint-founding-hypothesis)<a href="https://agentmods.dev/skills/product-on-purpose/pm-skills/tool-foundation-sprint-founding-hypothesis"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/tool-foundation-sprint-founding-hypothesis/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/product-on-purpose/pm-skills/tool-foundation-sprint-founding-hypothesis"><img src="https://agentmods.dev/badge/skills/product-on-purpose/pm-skills/tool-foundation-sprint-founding-hypothesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00109 | $0.02306 |
| Opus 5.5 | $0.00044 | $0.00922 |
| Sonnet 5.5 | $0.00022 | $0.00461 |
| Haiku 4.5 | $0.00011 | $0.00231 |
Grade A, and why
tool-foundation-sprint-founding-hypothesis 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 1mo 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Foundation Sprint Founding Hypothesis
Day 2 end of a Foundation Sprint. The team compresses the full sprint output into a single canonical sentence plus a testable scorecard. This is the artifact the sprint exists to produce; everything before this skill was preparation. Without a ratifiable Founding Hypothesis, the sprint failed.
Family contract: docs/reference/skill-families/foundation-sprint-skills-contract.md. This skill is a member of foundation-sprint-skills.
When to Use
- Day 2 end of a Foundation Sprint.
- Magic Lenses is signed; top bet and backup are named.
- The team has 30-45 minutes left in Day 2 and the energy to write the sentence carefully.
When NOT to Use
- Magic Lenses did not produce a clear top bet. Return to Magic Lenses; the Founding Hypothesis cannot stabilize on an unstable top bet.
- The team wants to "polish the hypothesis later." The hypothesis must be ratified by end of Day 2 or the sprint output is incomplete. Polishing later means re-litigating; that defeats the sprint's purpose.
- The team wants to ratify a vague hypothesis to "ship the sprint." A vague hypothesis is worse than no hypothesis; it gives false confidence and burns trust when validation fails.
What This Skill Produces
A single bundled artifact with five sections:
- Founding Hypothesis statement: the single canonical sentence (strict template, no paraphrase).
- Assumption scorecard: 5-7 assumptions extracted from the hypothesis, each scored on current confidence and tagged with a best next test (3-10 accepted; recommended range is 5-7).
- Why we believe this: 3-5 bulleted points naming the evidence base.
- What could prove us wrong: 3-5 bulleted points naming the risks. This section is the test of whether the team is in love with the hypothesis or holding it with calibrated confidence.
- Recommended next validation step: Design Sprint, customer research, experiment, landing page test, or other. Names the specific test, owner, and timeline.
What ships with it
3 files 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.
- 1mo ago First seen · 177 lines · 109 tokens per session scan A d21fd391731a
tool-foundation-sprint-founding-hypothesis is a skill published in the GitHub repository product-on-purpose/pm-skills (763 stars, last pushed today), licensed Apache-2.0. It adds 109 tokens to every session and 2,306 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
agent-spec-generator
Write a production-ready spec for an AI agent: scope, tools and permissions, autonomy levels, stop rules, escalation, failure modes, evals, and rollout. Use when you are about to build, buy, or expand an AI agent and need engineering, legal, and leadership to agree on what it may and may not do.
ai-ship-bar
Define a measurable quality bar for shipping an AI feature: task completion, precision and recall, p95 latency, cost per successful request, eval set design, thresholds, sign-off, regression gates, and post-launch monitoring. Use when an AI feature looks good in demos and you need to decide, with numbers, whether it…
opportunity-solution-trees
Use when asked to "opportunity solution tree", "OST", "Teresa Torres", "map customer opportunities to outcomes", "structure discovery around opportunities", or "compare solutions for a customer need". Helps product teams connect outcomes to customer opportunities and test solutions with Opportunity Solution Trees…
design-sprint
Use when asked to "run a design sprint", "5-day sprint", "prototype in a week", "test ideas before building", or "Jake Knapp sprint". Helps teams go from problem to tested prototype in five days. The Design Sprint framework (created by Jake Knapp at Google Ventures) compresses months of work into one focused week.
growth-loops
Use when asked to "growth loops", "build a growth engine", "design a viral loop", "create a content loop", "move beyond paid acquisition", or "why isn't growth compounding". Helps design self-reinforcing growth systems where output becomes input. The Growth Loops framework (from Brian Balfour / Reforge and Elena…
hierarchy-of-engagement
Use when asked to "define our core action", "North Star metric", "accruing benefits", "improve retention mechanics", "hierarchy of engagement", or "Sarah Tavel framework". Helps consumer products identify the actions and benefits that drive long-term retention. The Hierarchy of Engagement framework (created by Sarah…