A tool for saving short tasks or reminders in a wiki vault, a folder used for personal notes and reference pages. Notes have a type and due time, and expire automatically after seven days.

Use it to add, list, complete, or clear time-bound reminders and tasks, while updating the vault's note index and activity log.

It keeps temporary follow-ups separate from permanent documentation and surfaces active notes before they expire.

note — Skill for Claude Code by eliransu/digital-brain

Install

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.

Any agent

npx skills add eliransu/digital-brain --skill note

Clone the repo

git clone --depth 1 https://github.com/eliransu/digital-brain

Made for: Claude Code.

Or install digital-brain, the plugin that ships this one along with the rest of its 18 skills, 5 commands, 2 agents, 3 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eliransu/digital-brain/note/github.svg)](https://agentmods.dev/skills/eliransu/digital-brain/note)

Your own site

<a href="https://agentmods.dev/skills/eliransu/digital-brain/note"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/note/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/eliransu/digital-brain/note"><img src="https://agentmods.dev/badge/skills/eliransu/digital-brain/note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,508 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00154	$0.02508
Opus 5.5	$0.00062	$0.01003
Sonnet 5.5	$0.00031	$0.00502
Haiku 4.5	$0.00015	$0.00251

Measured 1mo ago against content hash efebd6583bfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

note 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.

skills/note/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

note: Time-Bound Reminders & Tasks in the Vault

Notes are the lightweight, ephemeral cousin of full wiki pages. Use them for "ping Carol about the demo tomorrow", "review red-team PR by Friday", "buy a new charger". They live for 7 days, then auto-expire.

User identity: [email protected]. Vault root: ~/digital-brain/.

Vault Layout

Notes folder: wiki/notes/ (create if missing)
Notes index: wiki/notes/_index.md (create if missing — table of active notes only)
Wiki index: wiki/index.md — has a ## Meta section; add [[notes/_index|Active Notes]] there once
Log: wiki/log.md — append a note entry at the TOP after every add/done
Hot cache: wiki/hot.md — touch ONLY if the note's due is within 24h

Invocation Forms

Form	Action
`/note <free-text>`	add (default kind = `reminder`)
`/note task <free-text>`	add with `note_kind: task`
`/note reminder <free-text>`	add with `note_kind: reminder` (explicit)
`/note list`	show active (non-expired, open) notes
`/note done <id-or-slug>`	mark a note as `done`
`/note clear`	manually sweep expired notes (auto on every invocation)

If $ARGUMENTS is empty, show the forms and ask which one.

Parsing `/note [kind] <tail>`

Kind. If the first tail token (case-insensitive) is task or reminder, consume it and set note_kind. Otherwise default note_kind: reminder.
Due time (by <when> / tomorrow / today HH:MM / <weekday> / in <N>h|d).
- by 18:00 or by 6pm → today at that time (or tomorrow if already past)
- tomorrow [HH:MM] → tomorrow at the given time or 09:00
- next <weekday> → next occurrence of that weekday at 09:00
- in 3h / in 2d → relative from now
- If nothing specified: default due = today 18:00 (or tomorrow 09:00 if it's already past 18:00).
Assignee (@<Person>). Default assignee: me. If @Name appears, resolve via wiki/entities/people/_index.md:
- If a person with that first-name alias or full-name match exists → assignee: "<Full Name>" and wikilink [[Full Name]] in the body.
- If not, apply the flywheel rule (see "Cross-Reference Rule" below): file the person first via the ppl skill with best-guess role, then link.
Title. The remaining text after stripping kind / by … / @Name is the title. Trim to ≤ 80 chars; full text stays in the body.

Read the full file on GitHub · 241 lines

Changes

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 · 241 lines · 154 tokens per session scan A efebd6583bfe

Subscribe to this mod's changes

note is a skill published in the GitHub repository eliransu/digital-brain (1 stars, last pushed 5mo ago), licensed MIT. It adds 154 tokens to every session and 2,508 once invoked, about $0.0006 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 2026-08-31.

Claude Code Productivity agent-skills claude-code-plugin cursor karpathy knowledge-base

llm-wiki

Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…

praneybehl/llm-wiki-plugin · 130 tokens

Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

agenticnotetaking/arscontexta · 50 tokens

open-migrate

Migrate settings between AI coding tools (Claude Code, Codex CLI, Cursor, Grok Build) — rules, skills, subagents, hooks, permissions. Also undoes a migration by run-id. Use when the user asks to move or import settings from one AI coding tool to another, or to roll one back.

chakki-the-potato/open-migrate · 70 tokens

x-to-obsidian

Capture high-signal X/Twitter posts into an Obsidian vault through the official Obsidian Web Clipper, then let LLM Wiki search, review, and promote the saved notes.

2233admin/obsidian-llm-wiki · 45 tokens

kb-preferences

Use when user wants to view, update, reset, or audit report preferences stored in vault kb.yaml. Triggers on '/kb-preferences', 'update report prefs', 'change report style', 'my preferences', or when a passive reflection step in another skill needs to propose preference updates.

rvk7895/llm-knowledge-bases · 62 tokens

stem

Plan first, build clean, keep every change on the record. Sizes every task (Quick / Standard / Initiative / High-stakes), keeps docs/planning and the worklog current, verifies work against intent, writes short scannable prose, and asks the human only at real decision points. Use at session start (/stem) or on any…

markskrypka/stem · 81 tokens