JasonWarrenUK/goblin-mode

5 stars · Last commit 2026-04-02

Three goblins in a trenchcoat pretending to be a senior developer. Claude Code config shaped by ADHD, friction, and spite.

README preview

# ~~Claude Code~~ <sup><ins>`goblin mode`</ins></sup>

![Goblin Mode](D6C1BA70-D6CD-40A0-8134-1DFED56D5A4D.png)

> [!CAUTION]
> 50% useful tool/teaching resource for agentic coding, 50% externalised temper tantrum.

**Goblin Mode** is a permanently-in-flux configuration system (skills[^1], agents, hooks) built by one developer to solve problems they actually had. Every skill traces back to a specific friction point. Hooks enforce habits that were being skipped.

[^1]: Skills replaced slash commands after Anthropic merged the two systems.

- **Weakness-aware design:** Testing is a known weakness, so a dedicated skill encodes the discipline. ADHD makes executive function unreliable, so hooks enforce it instead of relying on willpower.
- **Context window discipline:** CLAUDE.md loads every session. Skill descriptions load at start; bodies lazy-load on trigger. Agents run in sub-processes. Every layer has a deliberate cost.
- **Model tier thinking:** Skills specify whether they need Haiku (fast, cheap), Sonnet (balanced), or Opus (thorough). Not every task needs the biggest model.
- **Friction-driven, not architecture-driven:** This grew organically from actual work. The process of building it is what's transferable, not the specifics.

> [!NOTE]
> This setup is specific to one developer's workflow (and brain). If you're building your own, the **process** is what's transferable; the specifics should be yours.
>
> For the full story on how and why this was built, see [How to Use This Repo](docs/guides/HOW-TO-USE-THIS-REPO.md).

View full repository on GitHub →