Skip to content
Back to skills

Fnl Setup

ASecurity

User-run finolabs-vibecode host configuration and instruction files for Claude Code, Codex and Antigravity; add, instructions, check, scan, mode.

  • 4 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added November 6, 2026
ai-agents

Works with

  • claude code

Security analysis

A100/100

Pro scans all 14 files and shows the line behind each finding

Scanned November 11, 2026

npx -y skills add finolabs/finolabs-vibecode --skill fnl-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Fnl Setup?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Fnl Setup
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/finolabs-fnl-setup/badge)](https://www.skillsdirectory.com/skills/finolabs-fnl-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: fnl-setup
description: User-run finolabs-vibecode host configuration and instruction files for Claude Code, Codex and Antigravity; add, instructions, check, scan, mode.
disable-model-invocation: true
argument-hint: "[add <feature> | instructions | check | scan | mode [args]]"
---

# Set up finolabs-vibecode

Show `host.md` (local settings) and data root (settings/records folder) before approvals. Scopes: user account, project repository.

| Command (Codex: `$fnl-setup <word>`) | Loads |
| --- | --- |
| none | the core path below, then the menu |
| `add <feature>` | `references/features/<feature>.md` (menu below) |
| `instructions` | `references/instructions/procedure.md` |
| `check` | `references/check.md` (read-only), then stop |
| `scan` / `mode [args]` | `references/scan.md` / `references/mode.md` |

A plain sentence selects, never answers a consent question; "install everything" grants nothing. Ambiguous: one clarifying question, core, never several features at once. Codex forwarding is unverified; use sentences. User invocation: Claude Code enforced; otherwise advisory.

**Advisory (agent judgment):** Talk to the user in the language they are using, including questions and option labels; keep command names, flags, file paths, skill names and other technical names unchanged. All questions: native question tool/shape in `references/interview.md`; headless stays open.

## Core path

A bare run says: "Check: `/fnl-setup check` (read-only)." Show config/scan date; ask one scope question, user, project or both, recommendation first (user on a new computer, project in a repository that is not set up). Follow `references/core.md`.

Read-back: inert facts only; grants separate, beginner and Quick included, with no default.

Offer the beginner path: "Start with only the essential setup questions?"
Yes: Defer extras; no file changes/data sent.
No: Choose Advanced or Quick; switch later.
Undo: Switch paths; prior approvals stand.
Choices: "Yes, start with essentials" / "No, choose another path".
If yes: `references/plain-language.md`.
Otherwise **Advanced** asks each inert item; **Quick** confirms inert defaults once. Ask which.
In every mode these keep their own question: moving the data root and its copy; arming `auto` and the auto gate; filling host config; each Antigravity test-command grant; roles and review posting; the Antigravity hook write; each instruction-file write. In Quick mode unknowns stay open.

## Menu

After core, load [references/menu.md](references/menu.md) (`autopilot`, `compaction`).

Files in this skill

  • SKILL.md25.8 KB
  • references/check.md12.5 KB
  • references/companions.md2.5 KB
  • references/interview.md3.7 KB
  • references/plain-language.md2.7 KB
  • references/route-judge.md1.8 KB
  • scripts/checkup.py46.6 KB
  • scripts/compact_setup.py16.7 KB
  • scripts/compact_stop_setup.py13.9 KB
  • scripts/data_location.py5.7 KB
  • scripts/data_root.py7.6 KB
  • scripts/mode.py9.9 KB
  • scripts/quota_probe.py29.9 KB
  • scripts/quota_setup.py12.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.