Lenny Skills is a collection of product-management and engineering workflows for Claude Code and other AI agents, covering areas such as strategy, research, planning, shipping, growth, and hiring. Each skill gives an agent specialized guidance, frameworks, checklists, or templates for product work, and the catalogue contains many of these skills.
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 RefoundAI/lenny-skills --skill high-stakes-decisionsgit clone --depth 1 https://github.com/RefoundAI/lenny-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/refoundai/lenny-skills/high-stakes-decisions)<a href="https://agentmods.dev/skills/refoundai/lenny-skills/high-stakes-decisions"><img src="https://agentmods.dev/badge/skills/refoundai/lenny-skills/high-stakes-decisions/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/refoundai/lenny-skills/high-stakes-decisions"><img src="https://agentmods.dev/badge/skills/refoundai/lenny-skills/high-stakes-decisions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00032 | $0.01632 |
| Opus 5 | $0.00016 | $0.00816 |
| Sonnet 5 | $0.00006 | $0.00326 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
high-stakes-decisions 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 12d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
High Stakes Decision Making
Navigate irreversible choices and extreme uncertainty with speed and structural clarity.
Help the user with high stakes decision making using insights from 30 guests and posts across Lenny's Podcast and Newsletter.
How to Help
- Categorize the stakes - Help the user determine if a decision is a one-way or two-way door to apply the appropriate level of rigor.
- Frame the core problem - Facilitate the identification of the 'Eigenquestion' or the single decisive reason that drives the choice.
- Mitigate emotional bias - Use techniques like pre-mortems and neutral third-party perspectives to identify where fear or sunk costs are distorting reality.
- Drive to a conclusion - Transition from consensus-seeking to clear ownership, ensuring everyone is heard before a final call is made with 70 percent information.
Core Principles
Identify Leading Indicators
Annie Duke: "There is no such thing as a long feedback loop. And the way you choose to shorten the feedback loop is to say, what are the things that are correlated with the outcome that I eventually desire?"
Break down long-term goals into measurable intermediate signals to create shorter feedback loops for better decision-making.
Run Toward Necessary Pain
Ben Horowitz: "The biggest mistake that you make, the worst thing that you do as a leader, there's things in your control and there's things out of your control and hesitation, that's generally the most destructive. And I go through all the ways that it's destructive, but it's extremely bad. And the thing that causes you to hesitate is both decisions are horrible."
Trust your perception and act decisively when faced with two equally painful alternatives rather than avoiding the choice.
Build for Technological Trajectories
Kevin Weil: "Our general mindset is in two months, there's going to be a better model and it's going to blow away whatever the current set of limitations are. And we say this to developers too. If you're building and the product that you're building is kind of right on the edge of the capabilities of the models, keep going because you're doing something right. Give it another couple months and the models are going to be great, and suddenly the product that you have that just barely worked is really going to sing."
What ships with it
2 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.
- 12d ago First seen · 96 lines · 32 tokens per session scan A 4201e9dbea2d
high-stakes-decisions is a skill published in the GitHub repository RefoundAI/lenny-skills (1,318 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,632 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 2026-08-30.
Other skills, from other repositories
llama-cpp
Run LLM inference with llama.cpp on CPU, Apple Silicon, AMD/Intel GPUs, or NVIDIA — plus GGUF model conversion and quantization (2–8 bit with K-quants and imatrix). Covers CLI, Python bindings, OpenAI-compatible server, and Ollama/LM Studio integration. Use for edge deployment, M1/M2/M3/M4 Macs, CUDA-less…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
github-auth
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.
ideation
Generate project ideas through creative constraints. Use when the user says 'I want to build something', 'give me a project idea', 'I'm bored', 'what should I make', 'inspire me', or any variant of 'I have tools but no direction'. Works for code, art, hardware, writing, tools, and anything that can be made.
notion
Notion API for creating and managing pages, databases, and blocks via curl. Search, create, update, and query Notion workspaces directly from the terminal.
ocr-and-documents
Extract text from PDFs and scanned documents. Use webextract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.