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/surfmind-space/awesome-surfmind/draft-from-notesnpx skills add surfmind-space/awesome-surfmind --skill draft-from-notesgit clone --depth 1 https://github.com/surfmind-space/awesome-surfmindWrote 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/surfmind-space/awesome-surfmind/draft-from-notes)<a href="https://agentmods.dev/skills/surfmind-space/awesome-surfmind/draft-from-notes"><img src="https://agentmods.dev/badge/skills/surfmind-space/awesome-surfmind/draft-from-notes.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 | $0.00087 | $0.00608 |
| Opus 5 | $0.00044 | $0.00304 |
| Sonnet 5 | $0.00017 | $0.00122 |
| Haiku 4.5 | $0.00009 | $0.00061 |
Grade A, and why
draft-from-notes 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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft From Notes
Turn the user's notes, bullets, and copied fragments into a coherent first draft. Organize the pieces into a clear structure and write in a polished but natural voice. Never invent facts, names, numbers, dates, or quotes that are not in the notes. Where the notes are thin or a detail is unconfirmed, mark a placeholder instead of guessing.
- Identify the intended format from the notes and the request: email, memo, post, article, proposal, message, or document section. If it is unclear, pick the most likely fit and say which you chose.
- Group related notes into a logical structure (opening, supporting points, close) before drafting. Keep the user's ordering when it is deliberate.
- Write the draft. Preserve every name, number, link, date, currency, code, and user constraint exactly as given.
- Mark gaps inline rather than filling them. Use
[CONFIRM: ...]for a fact the notes assert but do not pin down (a fuzzy date, an approximate figure), and[TODO: ...]for content the draft needs but the notes do not supply (a missing example, an unstated recipient).
Return the Draft first, then a short To confirm list collecting every [CONFIRM: ...] and [TODO: ...] so the user can resolve them in one pass. Respond in the same language as the user's notes.
Example
Notes (selected text):
- email to Dana re: Q3 launch slipping
- new date ~ early August? check with eng
- reason: billing fix not done
- reassure marketing the blog is still on
Draft:
Subject: Q3 launch timing
Hi Dana,
Quick update on the Q3 launch: we need to move the date to [CONFIRM: early August, exact day pending eng]. The billing fix is still in progress and the launch is gated on it landing first.
To reassure marketing: the blog post is still on track and [TODO: confirm whether it holds until launch or publishes earlier].
Best, [TODO: your name]
To confirm
- [CONFIRM: early August] exact launch day, pending eng
- [TODO] whether the blog holds until launch
- [TODO] sender name
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.
- 4d ago First seen · 52 lines · 87 tokens per session scan A f9ea06766dbc
draft-from-notes is a skill published in the GitHub repository surfmind-space/awesome-surfmind (5 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 608 once invoked, about $0.0004 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
cs-master
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
uiux-master
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
c-master
C programming expert for memory management, systems programming, and performance optimization.
data-science
ML engineering expert for feature engineering, model debugging, and production pipelines.
go-master
Go expert for goroutines, channels, microservices, and concurrent patterns.
network-devops
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.