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/content-draftnpx skills add msolecki/founder-os --skill content-draftgit clone --depth 1 https://github.com/msolecki/founder-osWhat 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 | $0.00040 | $0.03129 |
| Opus 5 | $0.00020 | $0.01564 |
| Sonnet 5 | $0.00008 | $0.00626 |
| Haiku 4.5 | $0.00004 | $0.00313 |
Grade A, and why
content-draft 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 2d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Draft
A company of one has exactly one content advantage: specific, real, first-person experience with numbers attached. The migration that went wrong and what it cost. The client they fired and why. Everything else — the frameworks, the trends, the advice — competes against the entire internet and loses silently. Nobody tells the founder the post was boring. It just does nothing, forever.
So the bar is: does this contain something the founder learned by doing it? If not, don't publish it. Saying no is most of this skill's value; the founder can generate drafts endlessly and has no editor, which is exactly why the output drifts toward safe.
When to use
Against a slot in ## Plan with a source question. Not to fill a gap, not
because it has been a while, and not at 11pm when a prospect has annoyed them
into eloquence.
Inputs
Read first, in order — house rule 1:
-
content.md— the## Planslot: which question this answers, for whom, and on which channel. The channel is not a delivery detail decided after the writing; it is the length, the shape, and whether the first line has to work alone.content-planalready decided it — do not re-decide it here. -
content.md## Audience— their verbatim words. Write in those, not in the founder's internal vocabulary. -
voice.md—## Samples,## Tells,## Never,## Register. This and## Audienceare not the same input and they do not conflict: the audience's quotes decide which words the piece uses, the founder's samples decide how the sentences go. A piece in the founder's vocabulary is unreadable to the buyer; a piece in the founder's voice is why anyone reads a solo founder at all.## Registercovers the public post, which is the loosest register in the file and the one furthest from a proposal.If
## Samplesis empty, say so on the handoff — "no voice samples on record; this is a competent post by nobody in particular" — and hand the foundervoice-capture(Brand Editor). A published piece in a default register does not just underperform, it teaches the audience that this founder sounds like everyone else, and that impression is expensive to reverse. -
offer.md— the ICP. The reader is one specific person. -
clients/andpipeline.md— the specific thing that actually happened, with the number attached
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.
- 2d ago First seen · 243 lines · 40 tokens per session scan A b4fecf84081a
content-draft is a skill published in the GitHub repository msolecki/founder-os (4 stars, last pushed 8d ago), licensed MIT. It adds 40 tokens to every session and 3,129 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 2026-08-31.
Other skills, from other repositories
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
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.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
pedagogy-review
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…
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…