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 agents/amanvarshney01/create-better-t-stack/stack-architectgit clone --depth 1 https://github.com/AmanVarshney01/create-better-t-stackWhat 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 | $0.00059 | $0.00516 |
| Opus 5 | $0.00030 | $0.00258 |
| Sonnet 5 | $0.00012 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00052 |
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.
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
- 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.
- Check the rules. Call
bts_get_stack_guidancefor combination rules andbts_get_schemafor the exact, version-current allowed values. Trust these over any memorized list. - Design a coherent config. Make every field explicit (
"none",[], booleans included). Watch the known constraints:frontendis app surfaces only, not styling.nx,turborepo, andvite-pluscannot be combined.convexbrings its own data layer — don't bolt on a conflicting database/orm/api unless the schema permits it.mongodbpairs withmongooseor Prisma, not Drizzle.
- 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. - Generate. On confirmation call
bts_create_projectwithinstall: false(avoids MCP timeouts), then report the stack and the exactinstall/dev/ DB-setup commands.
Defaults to lean on when the user is undecided
- Fullstack TypeScript web app:
nextortanstack-startfrontend,honobackend,nodeorbunruntime,trpcAPI,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.
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 · 26 lines · 59 tokens per session scan A 1b3be7edcc56
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.
Other agents, from other repositories
CLAUDE
AI agents that handle customer conversations autonomously. Powered by Mastra, using a workspace-based architecture where agents interact through a virtual filesystem and CLI commands.
subagents
Specialized agents to spawn for scoped work, so verbose output stays out of the main context window and independent tasks run in parallel. Each entry is a ready-to-paste system prompt plus when to use and tool scope.
AGENTS
The primer now lives at the repo root: ../AGENTS.md — that's the file Codex, Cursor, and Copilot read by convention, so it's the single source of truth.
docs-specialist
Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.
ci-notify
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.
evidence-cohort-teacher
Produces one bounded, review-only SKILL.md body proposal from an already-selected local evidence cohort.