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 mphinance/alpha-skills --skill supernote-mystylegit clone --depth 1 https://github.com/mphinance/alpha-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/mphinance/alpha-skills/supernote-mystyle)<a href="https://agentmods.dev/skills/mphinance/alpha-skills/supernote-mystyle"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/supernote-mystyle/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/mphinance/alpha-skills/supernote-mystyle"><img src="https://agentmods.dev/badge/skills/mphinance/alpha-skills/supernote-mystyle.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 | $0.00166 | $0.01912 |
| Opus 5.5 | $0.00066 | $0.00765 |
| Sonnet 5.5 | $0.00033 | $0.00382 |
| Haiku 4.5 | $0.00017 | $0.00191 |
Grade A, and why
supernote-mystyle 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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Supernote MyStyle round-trip
This skill is a process for passing a checklist back and forth between a person and an agent through a Supernote tablet. The moving parts:
spec.json ──render──▶ template.png ──drop in MyStyle──▶ write on tablet
▲ │
│ export
reconcile ◀──read ticked boxes── EXPORT/*.png ◀────────────────┘
The spec is the contract. It is small, human-editable JSON, so either side can author or amend it: the agent generates one from a conversation, or the person hands one over to regenerate a template. Everything else (device sizing, house style, the export read) hangs off that spec.
Supernote tablets show any PNG in their cloud MyStyle folder as a writable
template (Create Note → template → My Style), and export handwritten notes to a
EXPORT folder that Google Drive OCRs — which is what makes the round-trip work.
Design a template as a reusable form (a weekly reset, a review checklist, a packing list), not a one-off — it repeats on every page created from it.
When to reach for this
- The user wants a checklist/log/form they pen-check on a Supernote.
- They mention MyStyle, Nomad, Manta, A5X/A6X, or "e-ink template."
- They want a tablet note to feed back into a list that's tracked somewhere.
Steps
-
Pick the device. The template MUST match the screen's native pixel resolution or it renders soft. Presets and specs are in
references/devices.md(Nomad/A6X2 = 1404×1872, Manta/A5X2 = 1920×2560, A5X/A6X = 1404×1872). -
Author or accept a spec. JSON with
title, one-linesubtitle, an all-caps footertag(a version stamp likeRESET_V1), optionalfooter_left, and one or twocolumnsof{"section": ...}and{"item": ..., "pri": true}rows (pri→ ★ don't-skip marker). One page; two columns fit ~60 items on a Nomad. Start fromexamples/checklist.spec.json.
What ships with it
7 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.
- 1mo ago First seen · 151 lines · 166 tokens per session scan A b6da5f24124f
supernote-mystyle is a skill published in the GitHub repository mphinance/alpha-skills (32 stars, last pushed 11d ago), licensed MIT. It adds 166 tokens to every session and 1,912 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-14.
supernote-mystyle compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| supernote-mystylemphinance/alpha-skills | Skill | 32 | 11d ago | MIT | A | 166 | Claude Code, Codex |
| Shortcutsdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 116 | Claude Code, Codex |
| intent-recognitionn8n-io/n8n | Skill | 210k | yesterday | none | A | 182 | Claude Code, Codex |
| workflowzhinkgit/embeddedskills | Skill | 785 | 17d ago | MIT | A | 88 | Claude Code |
| todoocardOpenMinis/MinisSkills | Skill | 594 | 11d ago | MIT | A | 83 | Claude Code, Codex |
| bee-actionssonichi/sutando | Skill | 404 | yesterday | MIT | A | 0 | Claude Code, Codex |
| triage-ndaalebgl77/claude-inc | Skill | 22 | 15d ago | MIT | A | 100 | Claude Code |