Better-T-Stack is a command-line tool that generates end-to-end, type-safe TypeScript project scaffolds from selectable frontend, backend, database, authentication, and tooling options. Developers use it to start full-stack applications with a stack tailored to their needs. The catalogue includes skills, agents, commands, an MCP server, and a plugin for having coding agents plan and generate Better-T-Stack projects.
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 AmanVarshney01/create-better-t-stack --skill better-t-stackgit clone --depth 1 https://github.com/AmanVarshney01/create-better-t-stackWrote 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/amanvarshney01/create-better-t-stack/better-t-stack)<a href="https://agentmods.dev/skills/amanvarshney01/create-better-t-stack/better-t-stack"><img src="https://agentmods.dev/badge/skills/amanvarshney01/create-better-t-stack/better-t-stack/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/amanvarshney01/create-better-t-stack/better-t-stack"><img src="https://agentmods.dev/badge/skills/amanvarshney01/create-better-t-stack/better-t-stack.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 | $0.00149 | $0.01253 |
| Opus 5.5 | $0.00060 | $0.00501 |
| Sonnet 5.5 | $0.00030 | $0.00251 |
| Haiku 4.5 | $0.00015 | $0.00125 |
Grade A, and why
better-t-stack 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 today.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Better-T-Stack
Better-T-Stack generates a type-safe TypeScript project from the parts the user picks: frontend, backend, runtime, API layer, database, ORM, auth, payments, addons and deploy targets. It rejects combinations that don't work, so let it build the project instead of writing the setup by hand.
Pick the interface
Use the first one you have:
| You have | Interface | It can |
|---|---|---|
bts_create_project tool |
Local MCP server | Plan, create and add, on disk |
| A shell | CLI: create-json and add-json |
Plan, create and add, on disk |
bts_get_create_command tool |
Hosted MCP server, https://www.better-t-stack.dev/mcp |
Plan and preview files, then return a command for the user to run |
| None of these | Stack Builder link | Prefill the visual builder for the user |
The hosted MCP server can't write files, can't change an existing project and doesn't accept addonOptions or dbSetupOptions. If the user needs any of those, give them the CLI command instead.
Create a project
If the folder already has a bts.jsonc, the project exists. Go to Change an existing project.
- Settle the stack. If the user left out a major choice (frontend, backend or database), ask one short question or propose defaults and confirm them. Don't add app surfaces, addons, examples or database provisioning the user didn't ask for.
- Get valid values from the tool, not from memory. Call
bts_get_schema, or runnpx create-better-t-stack@latest schema --name createInput. When the user has to choose, offer every valid option, not a subset. references/options.md lists the values and the compatibility rules that come up most, but the schema wins if they differ. - Build a full explicit config. Set every field. Use
"none",[],trueorfalseinstead of leaving a field out. - Plan before you write. Call
bts_plan_project, or runcreate-jsonwith"dryRun": true. If the plan fails, its error names the conflict. Fix the config and plan again. Show the user the planned stack and get a yes. - Create.
- Local MCP server:
bts_create_projectwithinstall: false. - CLI: the same
create-jsonpayload withoutdryRun, withinstall: false. - Hosted MCP server:
bts_get_create_command. Give the user the command to run in a terminal and stop here.
- Local MCP server:
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.
- today First seen · 65 lines · 149 tokens per session scan A ff018afdef9f
better-t-stack is a skill published in the GitHub repository AmanVarshney01/create-better-t-stack (5,831 stars, last pushed today), licensed MIT. It adds 149 tokens to every session and 1,253 once invoked, about $0.0006 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 2026-10-20.
Other skills, from other repositories
widen-return-type
When delegating a task affected by this skill, include.
scaffold-project
Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack. Use when the user wants to create, start, bootstrap, initialize, or generate a project from a stack description. Prefer the bundled Better Fullstack MCP server: guidance, schema…
refresh-generated
Regenerates code under generated/ from the schema. Use after schema.graphql changes.
regen-api-client
Regenerates the TypeScript API client with make client. Use after api/openapi.yaml changes; not for server stubs.
bun
Use this skill when building with Bun runtime — Bun APIs, testing, package management, shell scripting, hot reload, SQLite, file I/O. This skill enforces: built-in APIs over npm equivalents, Bun test runner, bun install speed optimization, Bun.shell for scripts. Do NOT use for: Node.js-specific APIs…
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…