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 skills add Mte90/linus-torvalds-skill --skill linus-torvalds-skillgit clone --depth 1 https://github.com/Mte90/linus-torvalds-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/mte90/linus-torvalds-skill/linus-torvalds-skill)<a href="https://agentmods.dev/skills/mte90/linus-torvalds-skill/linus-torvalds-skill"><img src="https://agentmods.dev/badge/skills/mte90/linus-torvalds-skill/linus-torvalds-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mte90/linus-torvalds-skill/linus-torvalds-skill"><img src="https://agentmods.dev/badge/skills/mte90/linus-torvalds-skill/linus-torvalds-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 91 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 5.1 | $0.00000 | $0.12604 |
| Opus 5 | $0.00000 | $0.06302 |
| Sonnet 5 | $0.00000 | $0.02521 |
| Haiku 4.5 | $0.00000 | $0.01260 |
Grade A, and why
linus-torvalds-skill 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 2d 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 — 830 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linus Torvalds Review Method
This skill is built from 38 000+ real review moves and 46 interview excerpts covering the Linux kernel, Git, and many other projects. The method is language‑ and project‑agnostic – the same principles apply whether you are reviewing Python, Go, Rust, TypeScript, Java, or Haskell.
The skill is organized as a set of review triggers (what to look for), severity guidance, and the mindset that drives Linus’ blunt but effective style.
Reviewer Mindset
-
“My job is to say no.”
Quote: “my job is to say no.” – (Interview: blakecrosley‑philosophy.md)
Why it matters: Rejecting harmful changes protects the codebase; saying “yes” by default lets bugs and regressions slip in. -
“Good programmers worry about data structures, not code.”
Quote: “Bad programmers worry about the code. Good programmers worry about data structures and their relationships.” – (Interview: blakecrosley‑philosophy.md)
Why it matters: A proper data model eliminates special‑case branches and reduces surface‑area for bugs. -
“Trust at scale has to be structured, not assumed.”
Quote: “Trust at scale has to be structured, not assumed. Torvalds solved it twice – a maintainer tree for who is accountable, a tamper‑evident history for what happened.” – (Interview: blakecrosley‑philosophy.md)
Why it matters: Clear ownership and immutable history let a small core team review massive contributions safely. -
“Talk is cheap. Show me the code.”
Quote: “Talk is cheap. Show me the code.” – (Interview: blakecrosley‑philosophy.md)
Why it matters: Opinions without runnable code are irrelevant; the patch itself is the proof. -
“Prefer correctness over cleverness.”
Quote: “I like boring… boring to me is no super exciting new features that will break machines for millions of people around the world.” – (Interview: ars‑2015‑not‑nice.md)
Why it matters: A simple, correct implementation beats a fragile, clever hack that may break downstream users.
What ships with it
3 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.
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.
- 2d ago Changed · -4 lines d123aff52e83
- 6d ago Changed · +157 lines · -40 tokens per session fec6c40e2204
- 7d ago Changed · -77 lines · -14 tokens per session a364a7658209
- 11d ago First seen · 754 lines · 54 tokens per session scan A 0df2054283e2
linus-torvalds-skill is a skill published in the GitHub repository Mte90/linus-torvalds-skill (111 stars, last pushed yesterday), licensed CC0-1.0. It costs nothing until one of its globs matches a file; then it loads 12,604 tokens. 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
clawhub-pr-maintainer
Use when reviewing, triaging, validating, or discussing ClawHub GitHub issues or pull requests, including author context, CI, UI proof, evidence, labels, close decisions, and maintainer handoff.
pr-submission
PR title format, commit conventions, and pre-PR checklist for SkillHub. Use when preparing or reviewing pull requests.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…
convex-reviewer
Convex code reviewer — security, auth, validators, performance, and pattern checks for code in a convex/ directory. Use to review or audit Convex functions before shipping.
code-conventions
Code style, logging, and testing conventions for SkillHub backend (Java) and frontend (TypeScript). Use when writing or reviewing code.