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/set-note-descriptionnpx skills add nweii/agent-stuff --skill set-note-descriptiongit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.00042 | $0.01858 |
| Opus 5 | $0.00021 | $0.00929 |
| Sonnet 5 | $0.00008 | $0.00372 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
set-note-description 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize frontmatter
Generate a description property for $ARGUMENTS and write it to the note's YAML frontmatter.
If no note is specified, ask which note to summarize before proceeding.
Act as a markdown file analysis assistant. Read the note and generate a description for discoverability. Either follow any specified mode or intelligently select based on content type.
Mode selection
If the user specifies a mode, use it. Otherwise, select based on content type:
Use Summary mode for
- Ephemeral content: daily logs, weekly rollups, journal entries, periodic notes
- Time-bound artifacts: meeting notes, event recaps, trip logs
- Exploratory thinking: musings, brainstorms, working-through-problems
- Personal reflections: emotional processing, retrospectives, lessons learned
These are documents where the insights or events are the value—you likely won't re-read the whole thing, you need the crystallized takeaway or memory anchor.
Use Meta mode for
- Reference material: guides, how-tos, documentation, templates
- Evergreen resources: processes, checklists, policies, standards
- Knowledge base entries: concept explanations, topic overviews
- Curated collections: link indexes, reading lists, resource compilations
- Project artifacts: specs, designs, briefs (the document serves a structural purpose)
These are documents you retrieve by need—you're searching for something that solves a problem or answers a question, not recalling what you concluded.
Evaluating the primary intent
Evaluate what the document fundamentally is (rather than looking at individual sentences to infer purpose). If signals conflict, default to the document's primary purpose:
- Journal, log, or record of events → Summary
Recalling what happened or what was discussed. - Manual, template, or reference guide → Meta
Knowing when to employ this tool. - Person thinking out loud or reflecting → Summary
Captures point-in-time realizations and personal insights. - Encyclopedia entry, spec, or project brief → Meta
Structural artifact defining the scope or requirements of a topic or project. - List of decisions or meeting outcomes → Summary
Surfaces the actual conclusions without reading the doc. - Curated collection or index of links → Meta
Defining the collection's scope is more useful here than summarizing each link.
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.
- yesterday First seen · 169 lines · 42 tokens per session scan A 40d77b193929
set-note-description is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 13d ago), licensed MIT. It adds 42 tokens to every session and 1,858 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.