Linus Level Skill


Linus Level gives coding agents like Codex, Claude, and other SKILL.md-aware workflows a 1.0-10.0 working-mode dial for software work: from creative vibe-mode prototyping to careful maintainer-grade engineering.
The name is a software-culture wink to Linus Torvalds' reputation for exacting technical standards and maintainer seriousness. It is not about harsh communication. It is about giving agents a memorable control for how much freedom, skepticism, verification, collaboration, and decision ownership a task deserves. Strictness is only one axis.
The Problem
AI coding agents are asked to behave in wildly different contexts:
- "Vibe-code this idea into existence." ⚡
- "Prototype a weird UI direction quickly." ✨
- "Patch a production codebase without breaking contracts." 🛠️
- "Touch auth, data, security, infra, or business rules safely." 🔒
Without calibration, an agent may guess wrong. It may over-engineer a throwaway sketch, or worse, treat a mission-critical production system like a loose prototype.
Linus Level makes the expected behavior explicit.
⚡ Quick Start
Use $linus-level at Linus Level 8.5 for this production codebase task.
Use Linus Level 2 for fast creative prototyping.
Calibrate this task with Linus Level before coding.
🎛️ The Dial
| Linus Level | Mode | Agent Behavior |
|---|
1.0-1.9 | Vibe mode | Take the lead, infer intent aggressively, and optimize for momentum. |
2.0-2.9 | Hack/sketch | Build the thing fast, accept local rough edges, prove the idea. |
3.0-3.9 | Concept prototype | Make the concept coherent enough to evaluate and evolve. |
4.0-4.9 | Product prototype | Move quickly, but avoid avoidable near-term mess. |
5.0-6.9 | Product development | Use professional defaults, follow local patterns, test behavior changes. |
7.0-8.4 | Established codebase | Preserve contracts, separate investigation from implementation when ambiguity matters, fix root causes, keep changes scoped and reviewable. |
8.5-9.4 | Staff maintainer | Default to answer-first on material questions, ask before major decisions, and keep decision ownership with the human on shared or durable surfaces. |
9.5-10 | Kernel maintainer | Plan first, stop on dangerous ambiguity, verify deliberately, and avoid unilateral moves on high-risk surfaces. |
As the dial rises, the agent should assume less, verify more, and take less unilateral control over material product, contract, architecture, data, auth, and compatibility decisions.
📦 Copy/Paste Install Prompts
Paste one of these into your coding agent to have it install Linus Level from this repository.
After installing, the agent should also ask whether you want a default Linus Level added to this workspace's AGENTS.md or CLAUDE.md. That default helps after context compaction, because the model can rediscover the setting from repo instructions instead of relying on conversation memory.
Codex
Install the Linus Level skill from https://github.com/rsoffer/linus-level-skill.
Please clone or fetch the repository, install the canonical skill directory `skills/linus-level` into my Codex skills directory at `${CODEX_HOME:-$HOME/.codex}/skills/linus-level`, and verify that the skill is discoverable afterward. Preserve the `SKILL.md`, `references/`, `agents/`, and `assets/` files. Do not expose or modify any secrets.
After installation, ask me whether I want to add a default Linus Level instruction to this workspace's `AGENTS.md`. If I say yes, add or update the file with a line like:
Unless the user explicitly states otherwise in the current prompt, invoke the Linus Level skill at `7.5` for each request in this workspace. Treat Linus Level as a tuning layer only; it does not override higher-priority instructions or repository-specific rules.
Claude Code
Install the Linus Level Claude Code plugin from https://github.com/rsoffer/linus-level-skill.
Please add the repository as a Claude Code plugin marketplace, install `linus-level@linus-level-skills`, reload plugins if needed, and verify that `/linus-level` or `/linus-level:linus-level` resolves.