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/nweii/agent-stuff/save-napkin-notenpx skills add nweii/agent-stuff --skill save-napkin-notegit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/save-napkin-note)<a href="https://agentmods.dev/skills/nweii/agent-stuff/save-napkin-note"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/save-napkin-note.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 5.1 | $0.00068 | $0.01808 |
| Opus 5 | $0.00034 | $0.00904 |
| Sonnet 5 | $0.00014 | $0.00362 |
| Haiku 4.5 | $0.00007 | $0.00181 |
Grade A, and why
save-napkin-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 5d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save napkin note
Turn capture material into a vault-ready note: template, frontmatter, folder, and related links. Sources:
- An existing note — inbox dump, partial draft, or rough file that needs finishing.
- Inline content — pasted or dictated text in the conversation (no file yet).
Fill in what is missing without overwriting work the user already did. Do not summarize away or discard ideas unless they ask.
Defer to AGENTS.md / CLAUDE.md
Canonical rules live there: vault layout, folder purposes, metadata semantics (including categories vs tags, date vs last, prev/next), hub vs content notes, and how to choose tools (Obsidian CLI, MCP, IDE, etc.).
This skill only adds procedure for one task: filing a capture. When in doubt on what a field means or where a note type belongs, read AGENTS.md rather than guessing.
Illustrative obsidian … commands below are examples for vaults where the CLI is wired; map them to your environment (read, properties, link-safe move/rename).
Arguments
$ARGUMENTS: If the source is a file, pass title or path. If the user only dumped text in chat, omit and use the message (or marked paste) as the body.- If vault file vs chat is ambiguous, ask once.
Analyzing the source
From a file: Read the full note with your vault tools.
From chat: Use the user’s message or the section they label as the capture.
Parse lightly: subject, entities (people, places, projects, dates, URLs), intent (event record vs concept vs reference vs active work), tone (fragment, decision log, meeting-shaped, etc.).
Candidate home note: For fragments or clear continuations, search the vault for a note this could extend. Never merge or append without explicit confirmation — see Integrate vs. new note.
Processing heuristics
1. Respect what exists
Only generate what is missing.
- Path (existing file): If the note is already outside a generic inbox/dump location, assume placement is intentional; do not move unless clearly wrong.
- Path (inline-only): No prior path — route using Routing captures below and AGENTS.md.
- Title: Keep a descriptive title; replace placeholders (
Untitled, bare timestamps) in the filing plan. - Frontmatter: If
tags,categories, etc. are already set, merge or leave alone — do not blindly replace.
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.
- 5d ago First seen · 160 lines · 68 tokens per session scan A 687317170de6
save-napkin-note is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 17d ago), licensed MIT. It adds 68 tokens to every session and 1,808 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…