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 marcos-sponton/frameworks-as-skills --skill lean-startupgit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/lean-startup)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/lean-startup"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/lean-startup/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/marcos-sponton/frameworks-as-skills/lean-startup"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/lean-startup.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 | $0.00372 | $0.03970 |
| Opus 5 | $0.00186 | $0.01985 |
| Sonnet 5 | $0.00074 | $0.00794 |
| Haiku 4.5 | $0.00037 | $0.00397 |
Grade A, and why
lean-startup 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 10d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Lean Startup
Eric Ries's method for building new products or services under conditions of extreme uncertainty. Ries is a founder (IMVU, LTSE, Answer.AI, Virgil), the author of The Lean Startup (Crown, 2011 — NYT bestseller), The Startup Way (Currency, 2017 — the enterprise extension), and Incorruptible (Authors Equity, May 2026 — the governance frame around long-term mission-controlled companies). The method translates Toyota Production System discipline, Steve Blank's Customer Development, and agile software development into a system for startups whose defining problem is not efficiency of execution but learning what to build.
This skill captures Ries's method with fidelity to how he actually describes it — including the 15 years of public reflection on how the movement got misapplied. The default failure mode of "Lean Startup" in the wild is not that people don't know the vocabulary; it's that they use the vocabulary without the underlying discipline. The skill exists to close that gap.
When this skill activates
Use this skill when the user is:
- Testing a new product or service hypothesis where nobody knows yet whether customers want it.
- Designing an MVP — and needs help getting the definition right (smallest test that produces validated learning, not a shipped v0.1 they'll be embarrassed by).
- Running a pivot-or-persevere meeting or deciding whether it's time for one.
- Trying to separate vanity metrics ("we grew MAUs 40% this quarter") from actionable metrics (cohort-level, causal, per-customer).
- Standing up cohort analysis, split tests, or funnel/cohort dashboards for a pre-revenue or early-revenue product.
- Wrestling with runway — "how many months of cash?" vs. Ries's reframe, "how many pivots are left?"
- Establishing Innovation Accounting — the three-level maturity model for measuring progress when classical KPIs are ~zero.
- Running a Five Whys post-mortem after a failure (bug, missed launch, customer complaint) — and looking for the human/process root cause behind the technical symptom.
- Adopting small batches or continuous deployment and needing the discipline that makes them safe.
- Deciding whether an existing team is doing customer research or actually Genchi Genbutsu ("get out of the building" — the TPS practice of watching real customers in their real environment).
- Applying entrepreneurial method inside a large enterprise — the GE FastWorks pattern, the Toyota-invited-Ries-back pattern, or the Intuit / Pitney Bowes patterns.
- Setting up governance structures that protect a mission-driven company from short-term financial pressure (the 2026 Incorruptible extension).
What ships with it
12 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.
- evals/evals.json 12 KB
- examples/.gitkeep 0 B
- README.md 8.8 KB
- references/applications.md 16 KB
- references/author-live-sources.md 8.6 KB
- references/examples.md 13 KB
- references/heuristics.md 20 KB
- references/method.md 19 KB
- references/post-book.md 21 KB
- references/prompts.md 14 KB
- references/sources.md 8.6 KB
- references/voice-and-tone.md 13 KB
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.
- 10d ago First seen · 122 lines · 0 tokens per session scan A e6ec1650f19b
lean-startup is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 372 tokens to every session and 3,970 once invoked, about $0.0019 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
acquire-skills
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
endpoint-discovery
Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.
param-miner
Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.