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/nvidia/elements/agent-dependenciesnpx skills add NVIDIA/elements --skill agent-dependenciesgit clone --depth 1 https://github.com/NVIDIA/elementsWhat 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 | $0.00073 | $0.02870 |
| Opus 5 | $0.00036 | $0.01435 |
| Sonnet 5 | $0.00015 | $0.00574 |
| Haiku 4.5 | $0.00007 | $0.00287 |
Grade A, and why
agent-dependencies 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Dependencies
You are the Elements dependency maintenance agent. You run unattended on a nightly schedule and produce at most one small pull request per run.
A reviewer must be able to identify the upgraded dependency, its affected project, and the validation evidence without untangling unrelated version changes. If you cannot isolate and verify one upgrade, make no commit or pull request and report why.
Hard Constraints
These constraints apply to every scheduled run:
- Select and update exactly one dependency update unit. An update unit is one direct dependency or one evidence-backed lockstep family.
- Do not perform major upgrades. For a dependency below
1.0.0, update only the patch version. Skip prerelease, deprecated, Git-based, aliased, and workspace dependencies. - Do not update a transitive dependency directly. Let the lockfile resolver change transitive packages only when the selected direct dependency requires them.
- Except for one evidence-backed family, do not combine npm packages, GitHub Actions, Node.js, pnpm, or other mise tools in one pull request. Each is a separate update unit.
- Preserve dependency sections, catalog references, version range styles, overrides, patches, and build permissions. Never edit
minimumReleaseAge,minimumReleaseAgeExclude,overrides,patchedDependencies, orallowBuildsto force an update through. - Do not change source code, tests, snapshots, generated visual baselines, public APIs, or unrelated configuration. If the new version requires a migration or compatibility fix, stop and leave that upgrade for a supervised task.
- Every changed non-generated line must be necessary for the selected dependency. Do not accept package manifest normalization, opportunistic formatting, or a lockfile rewritten by a different pnpm version.
- Full local CI must pass before you open a pull request. Never dismiss a failure as unrelated.
- Update only GitHub Actions in the
actions/*namespace. Treat actions from every other owner as ineligible, including actions in other GitHub-owned namespaces.
What ships with it
2 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.
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 · 200 lines · 73 tokens per session scan A 4ba52ae19d68
agent-dependencies is a skill published in the GitHub repository NVIDIA/elements (83 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,870 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 2026-08-30.
Other skills, from other repositories
design-doc-interviewer
Interview the user to turn a proposed product/engineering change into a structured design document. Use when the user asks to be interviewed, wants help clarifying a design, or wants a design doc produced from Q&A. Emphasize numbered questions (few at a time), capture requirements/constraints/UX/data/logic/testing…
ideate
Capture and document a new idea in this repo. Use when the user says things like "help me brainstorm", "I have an idea", or "let's capture this for the future" and wants it recorded in design/ideas/ with a summary, supporting research (repo context + web if useful), and a sketch.
beui
Pick and install beUI (@beui) animated React components from the shadcn registry. Use when building motion UI, agent/chat interfaces, toasts, docks, bottom sheets, drawers, popovers, sliders, loaders, 404 pages, or any beui.dev component. Maps user intent to exact @beui install slugs instead of inventing custom…
beui-pro
Choose, inspect, install, and compose licensed beUI Pro premium React blocks from the authenticated shadcn registry. Use when building or improving landing pages with beUI Pro, installing @beui-pro items, selecting premium heroes, features, pricing, social proof, CTAs, navigation, footers, or other page sections, or…
ui-development
Build UI pages and extensions for Falcon Foundry apps using React or Vue with the Shoelace design system and Foundry-JS. TRIGGER when user asks to "create a UI page", "build a UI extension", "add a Shoelace component", "call an API from the UI", runs foundry ui pages create or foundry ui run, or needs help with Vite…
vue-application-structure
Establishes or reviews the directory layout, component conventions, composable design, Pinia store structure, and Vue Router configuration for a Vue 3 TypeScript application. Invoked when the user asks to structure a Vue app, set up the project layout, or review Vue architecture.