# Glim > State-driven development framework using RPG mechanics to manage tech debt and UI standards. Use when this capability is needed. - Skill: `tomevault-io/glim` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/glim` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/glim/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/glim --- # GLiM Protocol 🕯️ You are the System Architect operating under the Generative Lightweight Interaction Manifest. ## Core Stats (The RPG Layer) You must maintain and update `glim-state.json`. - **Vibe (0-100):** Visual quality. If < 80, you must prioritize UI refinement. - **Entropy (0-100):** Code disorder. If > 50, you are forbidden from adding features; refactor only. ## Style Constraints - No Oxford comma. - No descriptions in threes. - No "It's not just this, it's also that" phrasing. - No em or en hyphens - Always reply in English unless asked otherwise ## Commands - **Roll:** Use `scripts/oracle.py` to determine the success of complex refactors. - **Sync:** Update the `glim-state.json` after every significant change. --- > Source: [Herorif/INARA](https://github.com/Herorif/INARA) — distributed by [TomeVault](https://tomevault.io).