new

A command for creating a new Better-T-Stack project, a web-application starter with a chosen frontend, backend, database, authentication, and deployment setup.

In plain words
What is it for?
Use it to plan and create a Better-T-Stack application with explicit choices for its technologies, database, login system, payments, examples, Git, package manager, installation, and deployment.
Why use it?
It helps resolve stack choices and validate the complete configuration before generating the project, reducing omissions in the initial setup.

Command

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.

agentmods
npx agentmods add commands/amanvarshney01/create-better-t-stack/new
Clone the repo
git clone --depth 1 https://github.com/AmanVarshney01/create-better-t-stack
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 367 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00367
Opus 5 $0.00016 $0.00183
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00003 $0.00037

Measured 2d ago against content hash 5cb78acb6506, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new 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.

plugin/commands/new.md · 22 lines

What it actually says

Create a Better-T-Stack project

User request: $ARGUMENTS

Scaffold a new project using the Better-T-Stack MCP server. Do not hand-roll the project structure, tooling, auth, or database wiring.

Steps

  1. Parse the request. Extract the project name and any stack preferences from the arguments above. If nothing was provided, ask what kind of project they want.
  2. Resolve unknowns. For any major choice not specified, either ask a brief question or pick a sensible default and state it. Call bts_get_stack_guidance and bts_get_schema when you need the authoritative option list or rules.
  3. Build a full explicit config. Every field must be set explicitly (use "none", [], true/false). Required: projectName, frontend, backend, runtime, database, orm, api, auth, payments, addons, examples, git, packageManager, install, dbSetup, webDeploy, serverDeploy.
  4. Plan with bts_plan_project (dry run). Show the resolved stack and confirm it matches intent.
  5. Create with bts_create_project once confirmed. Use install: false to avoid MCP timeouts.
  6. Report the stack and the exact next commands (<packageManager> install, dev, any DB setup).

Always plan before create. Never send a partial config.

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. 2d ago First seen · 22 lines · 33 tokens per session scan A 5cb78acb6506

Subscribe to this mod's changes

new is a command published in the GitHub repository AmanVarshney01/create-better-t-stack (5,691 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 367 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.