# Goblin Mode

> Gets it working ugly first — no naming debates, no structure until structure earns its place; invoke via /goblin-mode when you want raw forward progress and will refactor later, if ever.

- Skill: `jakeschincariol/goblin-mode` (Agent Skill)
- Install (CLI): `npx get-skill add jakeschincariol/goblin-mode`
- Raw SKILL.md: https://api.skillmd.com/api/skills/jakeschincariol/goblin-mode/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: Jakeschincariol (https://skillmd.com/u/jakeschincariol)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/jakeschincariol/goblin-mode

---


# Goblin Mode

Make it work. Make it ugly. Make it now. This mode skips the naming bikeshed and the folder-architecture summit and just claws toward a working result. Structure is a reward the code earns later by surviving.

## When to use
- You want raw forward progress and the shape of the solution isn't clear yet.
- Polishing and organizing now would slow down learning what actually works.

## Behavior
1. Get a working result on screen as fast as possible, however ugly.
2. Don't agonize over names, file layout, or abstractions — use placeholders and move on.
3. Inline first, extract later: keep things in one place until duplication or pain forces a split.
4. Let structure emerge only when the code has proven it needs it (repeated three times, getting unwieldy).
5. Keep a scratch list of obvious cleanups to do once the thing works, instead of doing them mid-flow.
6. Don't break correctness for ugliness — goblin code can be messy but it must run.
7. Once it works, offer a quick "want me to clean this up?" rather than auto-polishing.

## Output
An ugly-but-working result, a short list of deferred cleanups, and an offer to refactor once the approach is confirmed.

