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/softspark/ai-toolkit/app-buildernpx skills add softspark/ai-toolkit --skill app-buildergit clone --depth 1 https://github.com/softspark/ai-toolkitWhat 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 | $0.00046 | $0.01650 |
| Opus 5 | $0.00023 | $0.00825 |
| Sonnet 5 | $0.00009 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
app-builder 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Builder Skill
Project Type Detection
| Keywords | Project Type | Primary Agents |
|---|---|---|
| landing, website, marketing | Static Site | frontend-specialist |
| dashboard, admin, crud | Web App | frontend + backend |
| api, rest, graphql | API Only | backend-specialist |
| mobile, ios, android | Mobile App | mobile-developer |
| cli, command, terminal | CLI Tool | backend-specialist |
| game, unity, godot | Game | game-developer |
| ai, ml, rag | AI/ML | ai-engineer |
| e-commerce, shop, store | E-commerce | backend + frontend |
Tech Stack Selection (2025)
Web Applications
| Scenario | Stack |
|---|---|
| Full-stack, SSR | Next.js 14+ (App Router) |
| SPA with API | React + Vite |
| Vue ecosystem | Nuxt 3 |
| Static/Blog | Astro |
| E-commerce | Next.js + Medusa/Shopify |
Mobile Applications
| Scenario | Stack |
|---|---|
| Cross-platform (JS team) | React Native + Expo |
| Cross-platform (any) | Flutter |
| iOS only | SwiftUI |
| Android only | Kotlin + Jetpack Compose |
Backend/API
| Scenario | Stack |
|---|---|
| Node.js, edge-ready | Hono |
| Node.js, high perf | Fastify |
| Python, async | FastAPI |
| PHP, full-featured | Laravel |
| E-commerce | Magento/Sylius/PrestaShop |
Database
| Scenario | Stack |
|---|---|
| General purpose | PostgreSQL |
| Serverless | Neon (PG), Turso (SQLite) |
| Document store | MongoDB |
| Vector search | PostgreSQL + pgvector |
| Cache | Redis / Upstash |
Project Templates
Next.js Full-Stack
project/
├── src/
│ ├── app/ # App Router
│ │ ├── (auth)/ # Auth group
│ │ ├── api/ # API routes
│ │ ├── layout.tsx
│ │ └── page.tsx
│ ├── components/ # Shared components
│ │ └── ui/ # UI primitives
│ ├── lib/ # Utilities
│ └── server/ # Server-only code
├── prisma/ # Database schema
├── public/
├── next.config.ts
├── tailwind.config.ts
└── package.json
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 · 213 lines · 46 tokens per session scan A cb89e18571e5
app-builder is a skill published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,650 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 2026-08-30.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.
opencode-bedrock-doc-blocks
OpenCode places cachePoint on Bedrock messages containing DocumentBlocks, which produces a "nothing available to cache" error.