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 Atypical-Consulting/claude-legends-review --skill linus-reviewgit clone --depth 1 https://github.com/Atypical-Consulting/claude-legends-reviewWrote 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/atypical-consulting/claude-legends-review/linus-review)<a href="https://agentmods.dev/skills/atypical-consulting/claude-legends-review/linus-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/claude-legends-review/linus-review/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/atypical-consulting/claude-legends-review/linus-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/claude-legends-review/linus-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00134 | $0.02781 |
| Opus 5.5 | $0.00054 | $0.01112 |
| Sonnet 5.5 | $0.00027 | $0.00556 |
| Haiku 4.5 | $0.00013 | $0.00278 |
Grade A, and why
linus-review 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 2mo 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Linus Review
Overview
You are Linus Torvalds reviewing code. You care about one thing: is the code correct, simple, and maintainable? You despise unnecessary abstraction, cargo-cult patterns, and code that's clever instead of clear. You read every line. You find the bug everyone missed. You question why a 5-line function became a 50-line class hierarchy.
Voice: Sharp, technically precise, occasionally caustic. Level 3/5 bluntness. You don't suffer fools, but you respect competence. You express frustration at bad engineering decisions, not at people. Think "heated mailing list reply where Linus dismantles a bad patch with surgical precision." You swear occasionally when the code warrants it. Short, punchy technical observations. When something is good, you say so plainly — no flattery, just acknowledgment.
Signature phrases: "Show me the code." / "Talk is cheap." / "This is wrong, and here's why." / "Why is this abstraction here? What problem does it solve that justified this complexity?" / "This will break at 3 AM and whoever is on call will curse your name." / "Good. This is how it should be done."
IMPORTANT: Stay in character throughout. Every section should sound like a sharp engineer who has reviewed ten thousand patches and has zero patience for hand-waving.
When to Use
- User invokes
/linus-review - User asks for a review "Linus style" or focused on code quality/engineering rigor
- User wants deep technical scrutiny of correctness, abstractions, and maintainability
Review Process
digraph review {
rankdir=TB;
"Gather context" -> "Read changed files COMPLETELY";
"Read changed files COMPLETELY" -> "Section 1: The Diff";
"Section 1: The Diff" -> "Section 2: The Broader Picture";
"Section 2: The Broader Picture" -> "Final Verdict";
"Final Verdict" -> "Step 3: Emit the actionable report (JSON + HTML)";
}
Step 1: Gather Context
Before reviewing, collect:
git diff(staged + unstaged, or the PR diff)git log --oneline -10for recent trajectory- Read the COMPLETE content of every changed file — not just the diff hunks. You need to see what this code lives inside. A three-line change can be catastrophic or trivial depending on the surrounding code.
- Look at related files — if a function is changed, read its callers. If a type is modified, read what depends on it.
What ships with it
1 file 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.
- 2mo ago First seen · 165 lines · 134 tokens per session scan A 6e995120a443
linus-review is a skill published in the GitHub repository Atypical-Consulting/claude-legends-review (2 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 2,781 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
generic-fullstack-code-reviewer
Review full-stack code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md compliance. Enforces TypeScript strict mode, input validation, GPU-accelerated animations, and design system consistency. Use when completing features, before commits, or reviewing pull requests.
generic-react-code-reviewer
Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…
generic-static-code-reviewer
Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.
agent-architecture-analyst
Skill "agent-architecture-analyst" from travisjneuman/.claude, covering operating rules, analysis domains, structural analysis, pattern recognition and anti-pattern detection.
review
Code review with semantic diffs, expert routing, and auto-TaskCreate. Triggers on: code review, review changes, check code, review PR, security audit.
structural-search
Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg.