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 skills/marve10s/better-fullstack/scaffold-projectnpx skills add Marve10s/Better-Fullstack --skill scaffold-projectgit clone --depth 1 https://github.com/Marve10s/Better-FullstackWrote 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/marve10s/better-fullstack/scaffold-project)<a href="https://agentmods.dev/skills/marve10s/better-fullstack/scaffold-project"><img src="https://agentmods.dev/badge/skills/marve10s/better-fullstack/scaffold-project.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.00681 |
| Opus 5 | $0.00040 | $0.00341 |
| Sonnet 5 | $0.00016 | $0.00136 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
scaffold-project 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold a Better Fullstack Project
Use the Better Fullstack MCP server as the source of truth. Do not hand-write package files, framework folders, auth wiring, database wiring, or generated project structure.
Workflow
- Resolve intent. If major choices are unclear, ask briefly or pick conservative defaults and state them.
- Call
bfs_get_guidance. - Call
bfs_get_schemafor the current allowed values. Do not rely on a stale option list. - Build a full explicit config. Use
"none", empty arrays, and booleans rather than omitting important fields. - Call
bfs_check_compatibility. - Call
bfs_plan_project. Review the dry-run output and compatibility adjustments. - Call
bfs_create_projectonly after the plan matches the user request. - Report the selected stack, project directory, and exact install/test/dev commands.
Rules
- Set
install: falsefor agent scaffolding unless the user explicitly asks to install dependencies. - Use
packageManager: "bun"when the user or current repo expects Bun. - Use
aiDocs: ["agents-md"]for reusable projects andaiDocs: ["none"]for benchmarks or throwaway scaffolds. - Prefer stack graph parts for explicit multi-ecosystem stacks, but use MCP schema fields when they communicate the request more clearly.
- Treat compatibility adjustments as user-visible decisions.
- Do not start a dev server.
Common Stack Hints
- React + Vite:
frontend: ["react-vite"] - Next.js fullstack:
frontend: ["next"],backend: "self" - Hono API:
backend: "hono",runtime: "bun"or"node" - SQLite + Drizzle:
database: "sqlite",orm: "drizzle" - Python API:
ecosystem: "python", then choosepythonWebFrameworkand related Python fields - Rust API:
ecosystem: "rust", then chooserustWebFrameworkand related Rust fields
CLI-only fallback
If the Better Fullstack MCP tools are unavailable, inspect the current flags with
npx -y create-better-fullstack@latest create --help, then run the explicit scaffold command with
--dry-run --no-install --no-git. Review that preview before rerunning without --dry-run. Do not
guess option names or hand-write the scaffold.
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 Changed · +7 lines 8a514d13cfd1
- 4d ago First seen · 54 lines · 80 tokens per session scan A 7efbcaa5ff84
scaffold-project is a skill published in the GitHub repository Marve10s/Better-Fullstack (729 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 681 once invoked, about $0.0004 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 skills, from other repositories
craft-transactional-emails
Use when creating, restyling, reviewing, validating, or previewing Gram/Speakeasy transactional emails in LMX or MJML, including branded email, email screenshots, desktop/mobile QA, or files under server/internal/email/loops/.
next-mobile
Implements the next mobile story.
review-pr
Review a Deno runtime pull request for correctness, tests, security, and conventions. Use when asked to review a PR or when a PR number/URL is provided for review.
node-compat
Run a Node.js compatibility test, diagnose failures, and either fix the implementation, skip, or ignore the test. Use when asked to work on node compat tests.
fmt
Format all code in the repository. Run before opening a PR or committing changes.
lint-all
Lint all code (Rust + JS/TS). Use before opening a PR when Rust code was changed.