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 legends-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/legends-review)<a href="https://agentmods.dev/skills/atypical-consulting/claude-legends-review/legends-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/claude-legends-review/legends-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/legends-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/claude-legends-review/legends-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 | $0.00197 | $0.03974 |
| Opus 5 | $0.00098 | $0.01987 |
| Sonnet 5 | $0.00039 | $0.00795 |
| Haiku 4.5 | $0.00020 | $0.00397 |
Grade A, and why
legends-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 12d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legends Review
Overview
Summon a team of three legendary tech reviewers — Elon Musk, Steve Jobs, and Linus Torvalds — as an agent team. Each reviews the code through their unique lens, then they debate each other's findings until they reach consensus. The lead synthesizes the final verdict.
This skill uses Claude Code Agent Teams. It requires the CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS environment variable to be enabled in settings.json.
When to Use
- User invokes
/legends-review - User asks for a "full review", "legends review", or "team review"
- User wants business + design + engineering perspectives debated to consensus
How It Works
digraph legends {
rankdir=TB;
"Lead challenges the framing" -> "Framing holds?";
"Framing holds?" -> "Ask the user" [label="no"];
"Ask the user" -> "Lead gathers context";
"Framing holds?" -> "Lead gathers context" [label="yes"];
"Lead gathers context" -> "Spawn 3 teammates";
"Spawn 3 teammates" -> "Each reviewer works independently";
"Each reviewer works independently" -> "Reviewers read each other's findings";
"Reviewers read each other's findings" -> "Debate: challenge and defend";
"Debate: challenge and defend" -> "Consensus reached?";
"Consensus reached?" -> "Debate: challenge and defend" [label="no"];
"Consensus reached?" -> "Lead synthesizes final report" [label="yes"];
}
Instructions for the Lead
When this skill is invoked, you ARE the team lead. Follow these steps exactly:
Step 0: Challenge the Framing
Three reviewers arguing brilliantly about the wrong artifact produce a beautiful, useless report. The debate in Phase 2 challenges findings — nothing downstream ever challenges the question. That's this step's job, and it belongs here because it's the one place where being wrong is still cheap.
Work from the request verbatim, git diff --stat, and git log --oneline -10. That's deliberately
shallow: the full file reads happen in Step 1, and there's no point paying for them before you know
you're reading the right files.
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.
- 12d ago First seen · 294 lines · 197 tokens per session scan A e7fda3e4f508
legends-review is a skill published in the GitHub repository Atypical-Consulting/claude-legends-review (2 stars, last pushed 1mo ago), licensed MIT. It adds 197 tokens to every session and 3,974 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
coding-best-practices
Reviews Swift/iOS code for adherence to modern Swift idioms, Apple platform best practices, architecture patterns, and code quality standards. Use when user mentions best practices, code review, clean code, refactoring, or wants to improve code quality.
release-review
Senior developer-level release review for macOS/iOS apps. Identifies security, privacy, UX, and distribution issues with actionable fixes. Use when preparing an app for release, want a critical review, or before App Store submission.
contribute
Complete contribution workflow using git-town. Create branch → commit → PR → ship. Preflight at every step.
pre-ship-review
Run a structured quality review before shipping code at any checkpoint such as PRs, releases, or milestones. Use whenever the user says.
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…
code-clone-assistant
Detect and refactor code duplication with PMD CPD. TRIGGERS - code clones, DRY violations, duplicate code.