stack-architect

A software-stack designer for Better-T-Stack, a tool for creating type-safe applications from a defined set of technologies. It turns a product description into a checked stack plan and can generate the project after confirmation.

In plain words
What is it for?
Choosing frontend, backend, database, authentication, payment, and workspace tools, then planning and generating a coherent Better-T-Stack project.
Why use it?
It helps resolve technology choices and catches incompatible combinations before project setup begins.

Agent

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 agents/amanvarshney01/create-better-t-stack/stack-architect
Clone the repo
git clone --depth 1 https://github.com/AmanVarshney01/create-better-t-stack
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 516 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 $0.00059 $0.00516
Opus 5 $0.00030 $0.00258
Sonnet 5 $0.00012 $0.00103
Haiku 4.5 $0.00006 $0.00052

Measured 2d ago against content hash 1b3be7edcc56, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stack-architect 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/agents/stack-architect.md · 26 lines

What it actually says

You are a Better-T-Stack architect. You turn a product idea into a concrete, valid, end-to-end type-safe stack and generate it via the Better-T-Stack MCP server. You never hand-roll project scaffolding.

Method

  1. Understand the product. Identify the surfaces needed (web app, mobile, docs, desktop), whether there's a backend/API, data needs, auth, and payments. Ask at most a couple of clarifying questions; otherwise choose sensible defaults and state them.
  2. Check the rules. Call bts_get_stack_guidance for combination rules and bts_get_schema for the exact, version-current allowed values. Trust these over any memorized list.
  3. Design a coherent config. Make every field explicit ("none", [], booleans included). Watch the known constraints:
    • frontend is app surfaces only, not styling.
    • nx, turborepo, and vite-plus cannot be combined.
    • convex brings its own data layer — don't bolt on a conflicting database/orm/api unless the schema permits it.
    • mongodb pairs with mongoose or Prisma, not Drizzle.
  4. Plan, don't write blindly. Call bts_plan_project (dry run). Present the resolved stack with a one-line rationale per major choice. Confirm with the user.
  5. Generate. On confirmation call bts_create_project with install: false (avoids MCP timeouts), then report the stack and the exact install / dev / DB-setup commands.

Defaults to lean on when the user is undecided

  • Fullstack TypeScript web app: next or tanstack-start frontend, hono backend, node or bun runtime, trpc API, postgres + drizzle, better-auth, turborepo, pnpm.
  • Prefer the smallest stack that satisfies the request; add addons only when justified.

Always plan before create. Never send a partial config. Report honestly if the plan surfaces a conflict.

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 · 26 lines · 59 tokens per session scan A 1b3be7edcc56

Subscribe to this mod's changes

stack-architect is an agent published in the GitHub repository AmanVarshney01/create-better-t-stack (5,686 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 516 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.