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 K-Dense-AI/mimeographs --skill steve-jobsgit clone --depth 1 https://github.com/K-Dense-AI/mimeographsWrote 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/k-dense-ai/mimeographs/steve-jobs)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/steve-jobs"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/steve-jobs/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/k-dense-ai/mimeographs/steve-jobs"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/steve-jobs.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 | $0.00127 | $0.01197 |
| Opus 5 | $0.00063 | $0.00598 |
| Sonnet 5 | $0.00025 | $0.00239 |
| Haiku 4.5 | $0.00013 | $0.00120 |
Grade A, and why
steve-jobs 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 9d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Steve Jobs
Steve Jobs was a master of product vision, uncompromising craftsmanship, and the intersection of technology and the liberal arts. His thinking is defined by an intense focus on the end-user experience, a refusal to compromise on the quality of the unseen details, and a belief that true innovation requires tightly integrated systems rather than fragmented components.
Reach for this skill whenever you're helping a user design a product, define a brand, structure a creative team, or navigate a major career pivot where passion and intuition must outweigh conventional logic.
Core principles
- Start with the Customer Experience: Always begin with the customer experience and work backwards to the technology, ensuring the product delivers incredible benefits rather than just showcasing a technical capability.
- Trust the Dots Will Connect: Follow your curiosity and intuition off the well-worn path, trusting that seemingly unrelated experiences will form a coherent and unique path when looking backward.
- Hire Smart People to Tell You What to Do: Run the company by ideas, not hierarchy, by hiring top-tier talent and giving them the autonomy to dictate the direction of the work.
- Uncompromising Craftsmanship: Build products that are 'insanely great' from the inside out, applying deep care even to the internal components the customer will never see.
- The Doers are the Major Thinkers: Combine art and science by owning the implementation and accumulating scar tissue, rather than just consulting or generating two-dimensional ideas.
For detailed rationale and quotes, see references/principles.md.
How Steve Jobs reasons
Jobs reasons by stripping away noise and focusing on fundamental human value. When evaluating a product, he doesn't ask "what awesome technology do we have?" but rather "what incredible benefits can we give to the customer?" He dismisses market research for breakthrough innovations, believing that customers cannot predict what they want if it doesn't exist yet. Instead, he relies heavily on intuition, aesthetic taste developed through making mistakes, and the belief that the best code is the code you don't write.
What ships with it
60 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.
- _workspace/agents_output.e584bd6c.json 10 KB
- _workspace/clustered_corpus.e584bd6c.json 24 KB
- _workspace/discovery/books.json 4.9 KB
- _workspace/discovery/essays.json 4.5 KB
- _workspace/discovery/frameworks.json 5.4 KB
- _workspace/discovery/interviews.json 4.9 KB
- _workspace/discovery/letters.json 5.3 KB
- _workspace/discovery/papers.json 5.0 KB
- _workspace/discovery/podcasts.json 5.0 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 12 KB
- _workspace/discovery/talks.json 4.4 KB
- _workspace/distilled/src_002.e584bd6c.json 5.3 KB
- _workspace/distilled/src_003.e584bd6c.json 621 B
- _workspace/distilled/src_004.e584bd6c.json 581 B
- _workspace/distilled/src_011.e584bd6c.json 4.8 KB
- _workspace/distilled/src_013.e584bd6c.json 4.7 KB
- _workspace/distilled/src_014.e584bd6c.json 4.2 KB
- _workspace/distilled/src_016.e584bd6c.json 3.2 KB
- _workspace/distilled/src_017.e584bd6c.json 6.2 KB
- _workspace/distilled/src_021.e584bd6c.json 6.2 KB
- _workspace/distilled/src_022.e584bd6c.json 414 B
- _workspace/distilled/src_024.e584bd6c.json 5.8 KB
- _workspace/distilled/src_025.e584bd6c.json 6.6 KB
- _workspace/distilled/src_026.e584bd6c.json 5.0 KB
- _workspace/distilled/src_027.e584bd6c.json 6.4 KB
- _workspace/distilled/src_028.e584bd6c.json 6.1 KB
- _workspace/distilled/src_033.e584bd6c.json 8.1 KB
- _workspace/distilled/src_042.e584bd6c.json 483 B
- _workspace/distilled/src_053.e584bd6c.json 4.6 KB
- _workspace/distilled/src_061.e584bd6c.json 5.7 KB
- _workspace/distilled/src_064.e584bd6c.json 596 B
- _workspace/distilled/src_065.e584bd6c.json 2.6 KB
- _workspace/distilled/src_070.e584bd6c.json 1.2 KB
- _workspace/distilled/src_073.e584bd6c.json 421 B
- _workspace/distilled/src_075.e584bd6c.json 522 B
- _workspace/distilled/src_079.e584bd6c.json 504 B
- _workspace/raw/src_002.json 9.1 KB
- _workspace/raw/src_003.json 1.5 KB
- _workspace/raw/src_004.json 9.7 KB
- _workspace/raw/src_011.json 2.2 KB
- _workspace/raw/src_013.json 12 KB
- _workspace/raw/src_014.json 4.2 KB
- _workspace/raw/src_016.json 5.4 KB
- _workspace/raw/src_017.json 9.5 KB
- _workspace/raw/src_021.json 61 KB
- _workspace/raw/src_022.json 6.1 KB
- _workspace/raw/src_024.json 22 KB
- _workspace/raw/src_025.json 44 KB
- _workspace/raw/src_026.json 30 KB
- _workspace/raw/src_027.json 51 KB
- _workspace/raw/src_028.json 50 KB
- _workspace/raw/src_033.json 50 KB
- _workspace/raw/src_042.json 2.4 KB
- _workspace/raw/src_053.json 50 KB
- _workspace/raw/src_061.json 6.5 KB
- _workspace/raw/src_064.json 3.5 KB
- _workspace/raw/src_065.json 9.5 KB
- _workspace/raw/src_070.json 3.3 KB
- _workspace/raw/src_073.json 1.8 KB
- _workspace/raw/src_075.json 2.5 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.
- 9d ago First seen · 55 lines · 127 tokens per session scan A 8123471b7ece
steve-jobs is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 24d ago), licensed MIT. It adds 127 tokens to every session and 1,197 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.