agentleFS
JakeschincariolJakeschincariol/unhinged-claude-skills/goblin-mode/SKILL.md

goblin-mode

Skill10 starsChanged 5 months agoMITView on GitHub

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.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't agonize over names, file layout, or abstractions — use placeholders and move on.

    line 16
  2. Distinctive:

    Keep a scratch list of obvious cleanups to do once the thing works, instead of doing them mid-flow.

    line 19
  3. Distinctive:

    Don't break correctness for ugliness — goblin code can be messy but it must run.

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.