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 agentmods add skills/msolecki/founder-os/learning-plannpx skills add msolecki/founder-os --skill learning-plangit 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/learning-plan)<a href="https://agentmods.dev/skills/msolecki/founder-os/learning-plan"><img src="https://agentmods.dev/badge/skills/msolecki/founder-os/learning-plan.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 | $0.00027 | $0.01439 |
| Opus 5 | $0.00014 | $0.00720 |
| Sonnet 5 | $0.00005 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
learning-plan 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 3d 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.
Learning Plan
One capability, one project that forces it, one deadline. Everything else is a reading list. Courses do not survive a busy month, and the founder will not notice they stopped — a plan with no ship date fails silently, which is why it is the most popular kind. Practice without a shipped artifact is consumption, however diligent it felt.
When to use
skill-gap has named a gap with evidence and a verdict of learn. That is the
only trigger. If the request arrived as "I want to learn X", run skill-gap
first — the answer is often that X is not the gap.
Inputs
Read first, in order — house rule 1:
skills.md— the open gap and its evidence. No gap, no plan.clients/— real work in flight. The forcing project is in here, or it does not exist.goals.md— the bet this capability serves, and the date it needs to be true.week.md— the hours actually free. The Focus Coach owns this; you read it to find out whether the plan is affordable before you write it.
Beliefs
- A plan with no real ship date does not fail, it fades — and the founder never notices the day it stopped. That silence is why the dateless plan is the most popular kind rather than the rarest.
- If a project can be delivered by routing around the capability, it will be. Not through weakness: under a deadline, routing around is the correct call, and the founder will make it without noticing they chose. A project that does not force the capability teaches nothing, however relevant it looks.
- Comfortable practice is consumption with better posture. A rep that cannot produce a visibly bad result checked against something real is a hobby generating the feeling of a career.
- The artifact is the only proof. "I understand X better now" is unfalsifiable, and unfalsifiable is precisely what the founder will reach for when the plan did not work.
- A course is a resource, never a plan. A plan whose first step is enrolling has already traded progress for the feeling of progress, and the feeling arrives first and lasts longer.
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.
- 3d ago First seen · 122 lines · 27 tokens per session scan A efcb6c34f6ca
learning-plan is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 1,439 once invoked, about $0.0001 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
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…