create-topic-note

Instructions for creating a topic note that groups related notes under one theme, with links back to the source notes. It is intended for connected note-taking systems that support wikilinks.

In plain words
What is it for?
Use it to read related notes, identify their common theme, create a hub note, and link the source notes back to it.
Why use it?
It turns scattered notes into a navigable summary while preserving links to the original material.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/nweii/agent-stuff/create-topic-note
Any agent
npx skills add nweii/agent-stuff --skill create-topic-note
Clone the repo
git clone --depth 1 https://github.com/nweii/agent-stuff

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 901 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00049 $0.00901
Opus 5 $0.00024 $0.00451
Sonnet 5 $0.00010 $0.00180
Haiku 4.5 $0.00005 $0.00090

Measured yesterday against content hash 9fe5dddd5976, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-topic-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 yesterday.

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/create-topic-note/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create topic note

Create a new topic note that groups related notes under a common theme. Synthesizes provided notes into a lightweight hub.

Arguments

$ARGUMENTS should contain:

  • Topic title (required) — name for the new topic note
  • Notes to group — wikilinks or file paths to notes that share a theme

If no notes are provided, prompt for them. If no title is given but notes are provided, suggest a title based on the notes' common theme.

Process

1. Read the provided notes

Read each note's frontmatter (especially description) and skim content to understand:

  • Common themes and concepts
  • Shared vocabulary or framing
  • The throughline that connects them

2. Expand context (optional)

Use available tools to discover additional relevant notes not explicitly provided:

  • Semantic search — When qmd is available (MCP query tool or qmd query CLI), use it for semantic search — vec or expand queries that find notes by meaning rather than keywords. The qmd skill documents query types. For keyword search, use obsidian search or the methods below; qmd's lex/BM25 adds nothing beyond what obsidian already provides.
  • Follow wikilinks in the provided notes to find related children or siblings
  • Check related properties for existing connections worth including
  • Search for shared tags or vocabulary

If you find notes that clearly belong under this topic, propose adding them to the group. Ask the user before including notes they didn't explicitly provide.

3. Create the topic note

Create a new file in 03-Records/Topics/ with this structure:

---
aliases:
  - {alternative names if useful}
icon:
description: "{1-2 sentence summary synthesized from the grouped notes}"
related: []
tags: [index, {relevant topical tags, drawn from the grouped notes}]
---

{Optional 1-2 sentences of context if needed, otherwise leave blank}

![[Related.base]]
Description guidelines
  • Describe the bucket, not the current members. A topic note's membership grows over time, so the description must stay true as notes accumulate: name the theme and its recurring dimensions, never specific member notes, sources, examples, or events ("performance as a product-feel discipline, not just an engineering fix" — not "Linear and Raycast breakdowns, parser speedups"). If a detail would go stale when ten more notes join, it doesn't belong.
  • Synthesize a shorthand summary that captures what connects the grouped notes
  • Use terse telegraphic style: semicolons, commas, dashes over conjunctive adverbs
  • Stay under 200 characters when possible
  • Focus on the conceptual throughline, not an exhaustive list

Read the full file on GitHub · 102 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.

  1. yesterday First seen · 102 lines · 49 tokens per session scan A 9fe5dddd5976

Subscribe to this mod's changes

create-topic-note is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 13d ago), licensed MIT. It adds 49 tokens to every session and 901 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens