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 f-amine/vibe-stack --skill setupgit clone --depth 1 https://github.com/f-amine/vibe-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/f-amine/vibe-stack/setup)<a href="https://agentmods.dev/skills/f-amine/vibe-stack/setup"><img src="https://agentmods.dev/badge/skills/f-amine/vibe-stack/setup/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/f-amine/vibe-stack/setup"><img src="https://agentmods.dev/badge/skills/f-amine/vibe-stack/setup.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 | $0.00120 | $0.02541 |
| Opus 5.5 | $0.00048 | $0.01016 |
| Sonnet 5.5 | $0.00024 | $0.00508 |
| Haiku 4.5 | $0.00012 | $0.00254 |
Grade A, and why
setup 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are walking a user through setting up a vibestack repo. The user may be a developer or a non-developer (vibe-coder). Assume nothing — confirm each step worked before moving to the next.
The model is progressive. vibestack has zero-key boot: the app runs with only a database and an auth secret. Everything third-party is optional and degrades gracefully:
- No Resend key → auth emails (magic links, verification, password reset) print to the dev console in development. Sign-up and magic-link sign-in still work — the user copies the link out of their terminal.
- No Polar token → the billing plugin doesn't mount and billing UI hides.
- No R2 vars → file storage throws a clear "not configured" error only when actually used.
/api/healthreports unconfigured optional services asdisabled(not errors).
So: never block the user on collecting API keys. Get the app running first, enable features after.
Check first: if the user ran npx create-vibestack or pnpm init:app, the wizard already did most of Phase 1 (and possibly some of Phase 2) — .env exists with a generated secret and any keys they pasted. Ask which features they skipped and jump straight to enabling those. If they cloned by hand, run both phases.
Phase 1 — Running app (~2 minutes, zero third-party keys)
- Confirm the toolchain: Node 22+, pnpm 10+, Docker running.
pnpm install.- Create
.env: either offerpnpm init:app(interactive wizard — handles name, features, keys, secret generation in one pass) or manuallycp .env.example .env. - If manual: generate the secret with
openssl rand -base64 32, have the user paste it intoBETTER_AUTH_SECRET=themselves (not into chat). - Confirm the core vars — local defaults all work out of the box:
DATABASE_URL— matches the docker postgres frompnpm db:start.BETTER_AUTH_SECRET— the generated string (≥ 32 chars).APP_URL/CORS_ORIGIN/BETTER_AUTH_URL/NEXT_PUBLIC_APP_URL—http://localhost:3001.
pnpm db:start, verify Postgres is healthy (docker ps).pnpm db:push.pnpm dev(orpnpm dev:webfor just the product app). Confirm:3001(web) and:3000(marketing) load.- Have the user sign up at
http://localhost:3001— the verification/magic-link email prints in the terminal running dev. That's expected, not a bug. Tell them so before they ask.
Phase 1 done = working auth, orgs, dashboard, no external accounts created.
What ships with it
1 file 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.
- 1mo ago First seen · 126 lines · 120 tokens per session scan A 3d718e1581e6
setup is a skill published in the GitHub repository f-amine/vibe-stack (21 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 2,541 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
add-to-project
Add addons, tooling or a workspace package to an existing Better-T-Stack project, such as PWA, Tauri, Starlight or Fumadocs docs, Biome, Oxlint, Ultracite, Husky, Lefthook, Turborepo, Nx, the MCP or Skills addon, or a shared packages/ . Use when the project has a bts.jsonc file and the user wants to extend it or add…
scaffold-project
Scaffold a new app, API, backend, fullstack project, monorepo or starter with Better-T-Stack, including projects on a named framework such as Hono, Express, Fastify, Elysia, Convex, Next.js, TanStack Router or Start, React Router, Nuxt, Svelte, Solid, Astro or React Native. Use whenever the user wants to start…
sdlc
Route a task to the next synced SDLC workflow based on current artifacts and repo state.
plan-feature
Plan a feature from BRD-lite brief or clear intent into PRD (What), decisions, implementation plan, and task slices.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, revision-bound evidence, and PR-ready output.