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/better-fullstacknpx skills add Marve10s/Better-Fullstack --skill better-fullstackgit clone --depth 1 https://github.com/Marve10s/Better-FullstackWhat 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 | $0.00071 | $0.01342 |
| Opus 5 | $0.00036 | $0.00671 |
| Sonnet 5 | $0.00014 | $0.00268 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
better-fullstack 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Better Fullstack
Use the Better Fullstack generator as the source of truth for starter generation. Do not hand-write a full starter when a trusted Better Fullstack interface can produce it.
Choose The Path
Use an already-available CLI by default. The benchmarked best framing is: map the stack, dry-run the CLI, then run the same non-interactive command for real.
Use MCP only when the user explicitly asks for MCP, when CLI access is unavailable, or when the request needs structured schema lookup beyond what a concise CLI command can safely express. If using MCP, start with bfs_get_guidance, then use schema, compatibility, plan, and create/add tools in that order.
Use a trusted Better Fullstack interface in this order:
- A local CLI path provided by the prompt or current repository.
- A preinstalled Better Fullstack command available on
PATH. - An attached Better Fullstack MCP server or tool.
- A command explicitly provided or approved by the user.
If none is available, ask the user for the command, service, tool, or docs source they want used. Do not invent a bootstrap command.
Default CLI Workflow
- Map the user's stack into Better Fullstack graph parts and flat flags.
- Build one non-interactive command.
- Run it with
--dry-run. - If the dry run succeeds, run the same command without
--dry-run. - If the CLI rejects a combination, adjust to the closest valid Better Fullstack stack and report the adjustment.
CLI Rules
- Create exactly the requested project directory, using a relative project name.
- Prefer
create <project-name> --part ...for explicit or multi-ecosystem stacks. - Pass
--no-install --no-gitfor agent-driven scaffolding unless the user explicitly asks for side effects. - Pass
--package-manager bunwhen the user or project expects Bun. - Pass
--ai-docs agents-mdfor reusable projects, or--ai-docs nonefor benchmarks and throwaway scaffolds. - Use
noneexplicitly for categories the user wants disabled. - Do not start a dev server.
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.
- 2d ago First seen · 124 lines · 71 tokens per session scan A 7ed7f318b081
better-fullstack is a skill published in the GitHub repository Marve10s/Better-Fullstack (726 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 1,342 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
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.
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
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.
supermemory
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for…