nucleus-apple-notes

nucleus-apple-notes is a skill for Codex from zish-rob-crur/nucleus-apple-mcp. It costs 59 tokens per session (548 once invoked), scanned A, original, MIT.

A macOS tool for searching, reading, editing, and managing Apple Notes, including note attachments.

In plain words
What is it for?
Use it to search notes by account or folder, read or change their content, create notes, and add or export attachments.
Why use it?
It avoids switching to the Notes app or handling note data manually when an automated task needs to find or update notes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: built for openclaw.

Good fit Use it to search notes by account or folder, read or change their content, create notes, and add or export attachments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zish-rob-crur/nucleus-apple-mcp/nucleus-apple-notes
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 zish-rob-crur/nucleus-apple-mcp --skill nucleus-apple-notes
Clone the repo
git clone --depth 1 https://github.com/zish-rob-crur/nucleus-apple-mcp

Made for: Codex.

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.

agentmods badge for nucleus-apple-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/zish-rob-crur/nucleus-apple-mcp/nucleus-apple-notes/github.svg)](https://agentmods.dev/skills/zish-rob-crur/nucleus-apple-mcp/nucleus-apple-notes)
Your own site
<a href="https://agentmods.dev/skills/zish-rob-crur/nucleus-apple-mcp/nucleus-apple-notes"><img src="https://agentmods.dev/badge/skills/zish-rob-crur/nucleus-apple-mcp/nucleus-apple-notes/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.

agentmods 80×15 button for nucleus-apple-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/zish-rob-crur/nucleus-apple-mcp/nucleus-apple-notes"><img src="https://agentmods.dev/badge/skills/zish-rob-crur/nucleus-apple-mcp/nucleus-apple-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 548 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00548
Opus 5 $0.00030 $0.00274
Sonnet 5 $0.00012 $0.00110
Haiku 4.5 $0.00006 $0.00055

Measured 11d ago against content hash 559337eb7bae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nucleus-apple-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 11d 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/nucleus-apple-notes/SKILL.md · 39 lines

What it actually says

Use nucleus-apple notes ... to search, read, update, and attach files to Apple Notes data.

Operating Stance

  • Prefer the installed nucleus-apple binary.
  • Fall back to uvx --from nucleus-apple-mcp nucleus-apple ... when only uvx is available.
  • Narrow search by folder or account when that scope is already known.
  • Read the note before destructive rewrites, attachment export, or ambiguous updates.
  • Prefer append operations for incremental edits; use destructive set operations only for explicit replacement or format conversion.
  • Include shared or recently deleted content only when the task explicitly asks for it.
  • Re-read the note after destructive writes or attachment changes when follow-up actions depend on current content.

Core Workflow

  1. Resolve account, folder, or note scope only as far as the task requires.
  2. Inspect current note state before risky edits or attachment work.
  3. Choose create vs append vs destructive set from references/decision-rules.md.
  4. Use references/commands.md for canonical command shapes.
  5. Use references/failure-modes.md when notes are locked, shared, or still ambiguous after search.

Task Routing

  • Search by text, folder, or note ID: read references/decision-rules.md#scope-and-search.
  • Choose append vs replace body: read references/decision-rules.md#mutation-choice.
  • Export or add attachments: read references/decision-rules.md#attachment-workflow.
  • Locked notes, shared notes, expensive plaintext search, or rewrite risk: read references/failure-modes.md.

Output / Escalation

  • Use --pretty for human inspection.
  • Use --include-body-html only when formatting or embedded attachment anchors matter.
  • Use --allow-destructive only alongside --set-plaintext or --set-markdown.
Files

What ships with it

4 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.

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.

  1. 11d ago First seen · 39 lines · 59 tokens per session scan A 559337eb7bae

Subscribe to this mod's changes

nucleus-apple-notes is a skill published in the GitHub repository zish-rob-crur/nucleus-apple-mcp (20 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 548 once invoked, about $0.0003 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 2026-08-30.