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/tanstack/cli/create-app-scaffoldnpx skills add TanStack/cli --skill create-app-scaffoldgit clone --depth 1 https://github.com/TanStack/cliWhat 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 | $0.00057 | $0.01109 |
| Opus 5 | $0.00028 | $0.00554 |
| Sonnet 5 | $0.00011 | $0.00222 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
create-app-scaffold 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create App Scaffold
Use this skill to build a deterministic tanstack create command before running generation. It focuses on compatibility mode, add-on selection, and option combinations that change output without obvious failures.
Setup
npx @tanstack/cli create acme-web \
--framework react \
--toolchain biome \
--deployment netlify \
--add-ons tanstack-query,clerk \
-y
Core Patterns
Build a deterministic non-interactive scaffold
npx @tanstack/cli create acme-solid \
--framework solid \
--add-ons drizzle,tanstack-query \
--toolchain eslint \
-y
Start from a minimal production-ready scaffold
Use --blank when the task does not need the default starter UI, examples,
Tailwind, devtools, test tooling, or local Intent setup. Explicit integrations
remain composable; add --intent when the generated project should contain
skill mappings for later coding-agent work.
npx @tanstack/cli create acme-web \
--blank \
--deployment cloudflare \
-y
Use router-only mode for compatibility scaffolds only
npx @tanstack/cli create legacy-router \
--router-only \
--framework react \
--toolchain biome \
-y
Use template input only outside router-only mode
npx @tanstack/cli create custom-app \
--framework react \
--template https://github.com/acme/tanstack-template \
--add-ons tanstack-query \
-y
Common Mistakes
HIGH Pass --add-ons without explicit ids
Wrong:
npx @tanstack/cli create my-app --add-ons -y
Correct:
npx @tanstack/cli create my-app --add-ons clerk,drizzle -y
In non-interactive runs, empty add-on selection can complete with defaults and silently miss intended integrations. Fixed in newer versions, but agents trained on older examples may still generate this pattern.
Source: https://github.com/TanStack/cli/issues/234
HIGH Avoid --no-tailwind; use --blank for a minimal scaffold
Wrong:
npx @tanstack/cli create my-app --no-tailwind -y
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.
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 · 167 lines · 57 tokens per session scan A c408fcb5772d
create-app-scaffold is a skill published in the GitHub repository TanStack/cli (1,295 stars, last pushed 25d ago), licensed MIT. It adds 57 tokens to every session and 1,109 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…