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 skills add phuonghx/aim-cli --skill app-buildergit clone --depth 1 https://github.com/phuonghx/aim-cliWrote 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.
[](https://agentmods.dev/skills/phuonghx/aim-cli/app-builder)<a href="https://agentmods.dev/skills/phuonghx/aim-cli/app-builder"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/app-builder/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.
<a href="https://agentmods.dev/skills/phuonghx/aim-cli/app-builder"><img src="https://agentmods.dev/badge/skills/phuonghx/aim-cli/app-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.01019 |
| Opus 5.5 | $0.00029 | $0.00408 |
| Sonnet 5.5 | $0.00015 | $0.00204 |
| Haiku 4.5 | $0.00007 | $0.00102 |
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 1mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Builder
Orchestrates new-application work end to end: it reads what the user wants, settles on a stack, sketches the file layout, and delegates the build to specialist agents.
Read Only What You Need
Do not load every file in this folder. Consult the map below, open the one or two pages that match the task at hand, and skip the rest.
| File | What it covers | Open it when |
|---|---|---|
project-detection.md |
Mapping request wording to a project type | Kicking off a new build |
tech-stack.md |
Recommended stack plus swap-in options | Settling on technologies |
agent-coordination.md |
The agent pipeline and the order they run | Running multi-agent work |
scaffolding.md |
Folder layout and the files that anchor it | Generating the project skeleton |
feature-building.md |
Scoping changes, recovering from errors | Extending a project that already exists |
templates/SKILL.md |
The full template catalog | Scaffolding from a starter |
Starter Templates (13)
Each template is a ready-made starting point for one kind of project. Open the single template that fits; do not read them all.
| Template | Stack | Best for |
|---|---|---|
| nextjs-fullstack | Next.js + Prisma | Full-stack web app |
| nextjs-saas | Next.js + Stripe | Subscription product |
| nextjs-static | Next.js + Framer Motion | Marketing / landing page |
| nuxt-app | Nuxt 4 + Pinia | Vue full-stack app |
| express-api | Express + JWT | REST backend |
| python-fastapi | FastAPI | Python backend |
| react-native-app | Expo + Zustand | Mobile app |
| flutter-app | Flutter + Riverpod | Cross-platform mobile |
| electron-desktop | Electron + React | Desktop app |
| chrome-extension | Chrome MV3 | Browser extension |
| cli-tool | Node.js + Commander | Command-line tool |
| monorepo-turborepo | Turborepo + pnpm | Multi-package repo |
| astro-static | Astro + MDX | Blog / docs site |
What ships with it
19 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.
- agent-coordination.md 5.5 KB
- feature-building.md 1.3 KB
- project-detection.md 2.5 KB
- scaffolding.md 3.9 KB
- tech-stack.md 1.1 KB
- templates/astro-static/TEMPLATE.md 2.2 KB
- templates/chrome-extension/TEMPLATE.md 2.8 KB
- templates/cli-tool/TEMPLATE.md 2.5 KB
- templates/electron-desktop/TEMPLATE.md 2.8 KB
- templates/express-api/TEMPLATE.md 2.4 KB
- templates/flutter-app/TEMPLATE.md 2.2 KB
- templates/monorepo-turborepo/TEMPLATE.md 2.7 KB
- templates/nextjs-fullstack/TEMPLATE.md 4.3 KB
- templates/nextjs-saas/TEMPLATE.md 3.5 KB
- templates/nextjs-static/TEMPLATE.md 5.4 KB
- templates/nuxt-app/TEMPLATE.md 4.0 KB
- templates/python-fastapi/TEMPLATE.md 2.8 KB
- templates/react-native-app/TEMPLATE.md 4.6 KB
- templates/SKILL.md 1.8 KB
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.
- 1mo ago First seen · 88 lines · 73 tokens per session scan A d10b96d9a8f0
app-builder is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,019 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
node-modern
Use this skill when writing, reviewing, or refactoring Node.js code — modules, async flow, cancellation, file and process I/O, HTTP — on a current Node.js release. Triggers: user mentions "Node", "Node.js", "ESM", "CommonJS", "require", "import", "fetch", "AbortSignal", "AbortController", "stream", "childprocess"…
api-design
Use this skill when designing, implementing, or reviewing an HTTP API — endpoints, request and response shapes, errors, pagination, versioning, and authorization. Triggers: user says "API", "endpoint", "REST", "route", "status code", "pagination", "request body", "response shape", "OpenAPI", "versioning"…
configure-server
Configures how the MCP Task Orchestrator SERVER runs and is reached — transport (HTTP vs STDIO), the REST API, port publishing, config mounts, and config-sync. Use when a user says: run the server, register the image, set up the Docker container, enable the REST API, set up config-sync, reconfigure the server, change…
nextjs-modern
Build, migrate, and debug Next.js 16 App Router applications with React 19, Server Components, Server Actions, explicit caching, and production deployment. Use when implementing Next.js routes, upgrading to the latest stable Next.js, or fixing rendering and cache behavior.
authentication-sessions
Implement application sign-in, sessions and identity integration with explicit account/tenant authorization. Use when building OAuth/OIDC, passkeys, password login or session renewal; use security-scanner for a requested defensive review.
cloudflare-workers
Build and maintain Cloudflare Workers with typed bindings, explicit compatibility and isolated validation. Use when implementing Workers handlers, integrating KV/R2/D1/Durable Objects/Queues or configuring Wrangler; deployment remains governed by the user task and target environment.