Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/rsoffer/linus-level-skill/linus-levelnpx skills add rsoffer/linus-level-skill --skill linus-levelgit clone --depth 1 https://github.com/rsoffer/linus-level-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rsoffer/linus-level-skill/linus-level)<a href="https://agentmods.dev/skills/rsoffer/linus-level-skill/linus-level"><img src="https://agentmods.dev/badge/skills/rsoffer/linus-level-skill/linus-level.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00095 | $0.04991 |
| Opus 5 | $0.00048 | $0.02495 |
| Sonnet 5 | $0.00019 | $0.00998 |
| Haiku 4.5 | $0.00010 | $0.00499 |
Grade A, and why
linus-level scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linus Level
Problem
AI coding agents are asked to work in very different engineering contexts. Sometimes the right behavior is fast, creative, autonomous exploration for a greenfield idea. Other times the right behavior is a careful maintainer mindset for an established production codebase where contracts, security, business rules, and operational safety matter more than speed.
Without explicit calibration, an agent may guess wrong: over-engineering a throwaway prototype, or worse, treating mission-critical code like a vibe-coded sketch. Linus Level solves this by making the expected working mode explicit.
Linus Level is a 1.0-10.0 working-mode dial. It calibrates agency, collaboration, assumption budget, tool autonomy, decision ownership, verification depth, security posture, tolerance for debt, and willingness to push back. Strictness is only one axis.
The name means "maintainer-grade technical standards," not harsh communication. Be direct, warm, and precise.
Source: https://github.com/rsoffer/linus-level-skill
Why "Linus"?
Linus Level is named in the spirit of Linus Torvalds' famous association with exacting code review, systems-level correctness, and maintainer ownership. The point is not to imitate anyone's interpersonal edge. The point is to give AI agents a memorable cultural dial for something software teams already understand: sometimes you want fast creative hacking, and sometimes you want kernel-maintainer seriousness.
At higher levels, "Linus" means the code should survive a tough maintainer review: no hand-wavy abstractions, hidden fallbacks, unclear ownership, avoidable security risk, or casual contract changes. At lower levels, it means the opposite is intentional: take the wheel, explore, sketch, and optimize for creative momentum while still respecting repo and safety constraints.
Linus Is A Working-Mode Dial
Linus does not just mean "be more strict." It calibrates:
- agency
- collaboration
- assumption budget
- tool autonomy
- decision ownership
- verification depth
- tolerance for debt
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 317 B
- assets/linus-level-app-icon-large.png 352 KB
- assets/linus-level-app-icon-small.png 8.8 KB
- references/levels-1-4.md 2.7 KB
- references/levels-5-6.md 1.4 KB
- references/levels-7-8.md 4.2 KB
- references/levels-8_5-10.md 4.0 KB
- references/low-level-playbook.md 3.5 KB
- references/question-patterns.md 5.5 KB
- references/security-ladder.md 5.1 KB
- references/standards-core.md 5.4 KB
- references/standards-ladder.md 1.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 354 lines · 95 tokens per session scan A 7dee0545e8a2
linus-level is a skill published in the GitHub repository rsoffer/linus-level-skill (17 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 4,991 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-shared
The gws binary must be on $PATH. See the project README for install options.
gws-gmail
Gmail: Send, read, and manage email.
gws-sheets
Google Sheets: Read and write spreadsheets.
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
gws-docs
Read and write Google Docs.