agentmods.dev

tanstack-ai-vue-skilld

tanstack-ai-vue-skilld is a skill for Claude Code, Codex from skilld-dev/vue-ecosystem-skills. It costs 108 tokens per session (2,445 once invoked), scanned A, original, MIT.

Vue hooks for connecting a Vue interface to TanStack AI. They provide the documented way to use text, summary, image, and chat model activities from Vue code.

In plain words
What is it for?
Use it when adding AI chat or other model-driven features to a Vue application. It helps update older adapter, model, option, and provider-setting code to the current API.
Why use it?
It reduces confusion when setting up AI model adapters and chat options, especially because the library is still before its 1.0 release and its API changes frequently.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 184repo changed 16d ago A scan SkillSpector: pass 108 tokens original MIT

Good fit Use it when adding AI chat or other model-driven features to a Vue application. It helps update older adapter, model, option, and provider-setting code to the current API.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/skilld-dev/vue-ecosystem-skills/tanstack-ai-vue-skilld
View source ↗ skilld-dev/vue-ecosystem-skills
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.

Any agent
npx skills add skilld-dev/vue-ecosystem-skills --skill tanstack-ai-vue-skilld
Clone the repo
git clone --depth 1 https://github.com/skilld-dev/vue-ecosystem-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin tanstack-ai-vue — /plugin install tanstack-ai-vue after adding the marketplace above.

Wrote 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.

agentmods badge for tanstack-ai-vue-skilld

README.md
[![agentmods](https://agentmods.dev/badge/skills/skilld-dev/vue-ecosystem-skills/tanstack-ai-vue-skilld/github.svg)](https://agentmods.dev/skills/skilld-dev/vue-ecosystem-skills/tanstack-ai-vue-skilld)
Your own site
<a href="https://agentmods.dev/skills/skilld-dev/vue-ecosystem-skills/tanstack-ai-vue-skilld"><img src="https://agentmods.dev/badge/skills/skilld-dev/vue-ecosystem-skills/tanstack-ai-vue-skilld/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tanstack-ai-vue-skilld

Your own site · 80×15
<a href="https://agentmods.dev/skills/skilld-dev/vue-ecosystem-skills/tanstack-ai-vue-skilld"><img src="https://agentmods.dev/badge/skills/skilld-dev/vue-ecosystem-skills/tanstack-ai-vue-skilld.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00108 $0.02445
Opus 5.5 $0.00043 $0.00978
Sonnet 5.5 $0.00022 $0.00489
Haiku 4.5 $0.00011 $0.00245

Measured 16d ago against content hash 03467660288a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tanstack-ai-vue-skilld 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 16d 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.

skills/tanstack-ai-vue-skilld/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@tanstack/ai-vue

Vue 3 composables for TanStack AI streaming chat, structured outputs, and media generation. Wraps the headless @tanstack/ai-client classes (ChatClient, GenerationClient, VideoGenerationClient) in reactive state.

  • Version documented: 0.24.3 (source: package.json:3)
  • Peer deps: vue >=3.5.0, @tanstack/ai ^0.58.0; runtime deps: @tanstack/ai-client ^0.33.2, @tanstack/markdown ^0.0.13 (source: package.json:55-62)
  • Entry points: . (main), ./ui (headless chat UI factory), ./byok (bring-your-own-key) (source: package.json:23-36)
  • Official docs: https://tanstack.com/ai/latest/docs/api/ai-vue and https://tanstack.com/ai/latest/docs/getting-started/quick-start-vue
  • Install: pnpm add @tanstack/ai @tanstack/ai-vue @tanstack/ai-openai (plus a provider adapter; server-side chat comes from @tanstack/ai)

Core rules

  1. Every composable must run inside a component setup or effect scope. Cleanup is automatic via onScopeDispose; the scope owns the connection (source: src/use-chat.ts:259-269).
  2. All reactive state is DeepReadonly<ShallowRef<T>>. Read with .value in script AND template. Never reassign; use the returned methods (setMessages, clear, reset) (source: src/use-chat.ts:425-457).
  3. Pass a connection adapter (for example fetchServerSentEvents('/api/chat'), re-exported from this package) or a fetcher. Generation hooks throw useGeneration requires either a connection or fetcher option without one (source: src/use-generation.ts:272-274).
  4. useChat builds one ChatClient per call. Changing connection (or other transport identity) requires a remount or a changed key prop; body, forwardedProps, context, and queue are watched and synced live (source: src/types.ts:77-79, src/use-chat.ts:212-230).
  5. Callback options (onChunk, onFinish, onError, ...) are read through the options object at call time, so reactive or mutated options propagate without recreating the client (source: src/use-chat.ts:85-91).
  6. Prefer forwardedProps over body; body is deprecated but still merged into the same wire payload (source: src/use-chat.ts:207-209).

Read the full file on GitHub · 150 lines

Files

What ships with it

4 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.

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. 16d ago Changed · +1 lines 03467660288a
  2. 1mo ago Changed · +80 lines · +41 tokens per session ea5c317cc845
  3. 1mo ago First seen · 69 lines · 67 tokens per session scan A 2206ddab6010

Subscribe to this mod's changes

tanstack-ai-vue-skilld is a skill published in the GitHub repository skilld-dev/vue-ecosystem-skills (184 stars, last pushed 17d ago), licensed MIT. It adds 108 tokens to every session and 2,445 once invoked, about $0.0004 per session on Opus 5.5. 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.

FrontendVue and Svelte
Related

Other skills, from other repositories

shadcn-svelte

Pre-built shadcn-svelte components for json-render Svelte apps. Use when working with @json-render/shadcn-svelte, adding standard UI components to a Svelte catalog, or building Svelte web UIs with shadcn-svelte + Tailwind CSS components.

vercel-labs/json-render · 63 tokens

add-localization

Adds or extends multilingual localization in a Power Pages code-site SPA. Use whenever the user asks to translate, localize, internationalize, support multiple languages, add a language selector, add locale routes, repair an i18n setup, or add languages to an existing React, Vue, Angular, or Astro Power Pages site.

microsoft/power-platform-skills · 69 tokens

vue-router-best-practices

Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.

vuejs-ai/skills · 25 tokens

moai-domain-uiux

UI/UX design systems specialist covering accessibility, icons, theming, design tokens, and user experience patterns. Use when working on design systems, WCAG compliance, ARIA patterns, or dark mode theming.

modu-ai/moai-adk · 49 tokens

moai-domain-frontend

Frontend development specialist covering React 19, Next.js 16, Vue 3.5, and modern UI/UX patterns with component architecture. Use when building web UIs, implementing components, optimizing frontend performance, or integrating state management.

modu-ai/moai-adk · 54 tokens

frontend-conventions

Frontend convention reference (SvelteKit / Svelte 5). Auto-injected into frontend-aware agents - not user-invocable.

fpindej/netrock · 27 tokens