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-termnpx skills add nweii/agent-stuff --skill save-termgit 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 | $0.00076 | $0.01594 |
| Opus 5 | $0.00038 | $0.00797 |
| Sonnet 5 | $0.00015 | $0.00319 |
| Haiku 4.5 | $0.00008 | $0.00159 |
Grade A, and why
save-term 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save term
Save a term or phrase as a Term note in 02-Evergreen/Terms/. Two modes:
- Encountered — a term lifted from a book, article, conversation, or other external source. Body anchors on a source citation + quote.
- Coined — a term that emerged during conversation (often a compact replacement for a wordy phrase, or a fresh concept the user wants to lock in). Body is a brief gloss with a usage example or context.
This skill is not for general note-taking. It writes one specific shape of note — short, atomic, and aligned with the existing vault Term convention. For broader capture, use save-napkin-note.
Defer to AGENTS.md / CLAUDE.md
Vault layout, metadata semantics, and tool-choice rules live in the vault's AGENTS.md and CLAUDE.md. This skill only adds the procedure for writing one note type. When unsure about a field's meaning or which tool to use for vault writes, read those first.
Arguments
$ARGUMENTS: the term or phrase to save. If omitted, ask. If the term contains punctuation tricky for filenames (/,:, etc.), confirm a filesystem-safe variant before writing.
Process
1. Determine mode
Ask if not obvious from context:
- Encountered — user is referencing something external (a book, article, person they're quoting, web clipping). Need a source.
- Coined — emerged in this conversation, no external source. Likely came out of a phrase-revision pass or a fresh framing.
2. Gather what the body needs
For encountered terms:
- Source citation — wikilink to an existing vault note if possible (
[[Source note title]]), otherwise a markdown link to the URL with the article/book title as link text. Check04-Entities/and03-Records/Clippings/for an existing source note before defaulting to a raw URL. - Quote — verbatim passage from the source that defines or illustrates the term. Use a blockquote (
>). Don't paraphrase. - Optional: brief framing sentence above the quote if needed for context, though most existing Term notes go straight to the quote.
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.
- 2d ago First seen · 145 lines · 76 tokens per session scan A 096c8284e594
save-term is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 14d ago), licensed MIT. It adds 76 tokens to every session and 1,594 once invoked, about $0.0004 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…