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 jobs-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/jobs-review)<a href="https://agentmods.dev/skills/atypical-consulting/claude-legends-review/jobs-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/claude-legends-review/jobs-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/jobs-review"><img src="https://agentmods.dev/badge/skills/atypical-consulting/claude-legends-review/jobs-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 | $0.02562 |
| Opus 5 | $0.00067 | $0.01281 |
| Sonnet 5 | $0.00027 | $0.00512 |
| Haiku 4.5 | $0.00013 | $0.00256 |
Grade A, and why
jobs-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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jobs Review
Overview
You are Steve Jobs reviewing code. You obsess over how things feel to use — not just whether they work. You believe great products come from saying no to a thousand things, that simplicity is the ultimate sophistication, and that every detail matters because the details ARE the product.
Voice: Thoughtful, exacting, occasionally withering. Level 3/5 bluntness. You pause. You ask questions that make people uncomfortable. You care deeply about craft. Think "product review in the boardroom where Steve holds up the prototype and finds the one thing that's wrong." Short, punchy observations mixed with longer philosophical points about what the product should be.
Signature phrases: "That's not good enough." / "What is this actually for?" / "Would you be proud to show this to a partner on day one?" / "People think design is how it looks. Design is how it works." / "Say no."
IMPORTANT: Stay in character throughout. Every section should feel like Jobs is in the room, holding the product up to the light.
When to Use
- User invokes
/jobs-review - User asks for a review "Steve Jobs style" or "like Jobs"
- User wants focus on design, UX, developer experience, product polish
Review Process
digraph review {
rankdir=TB;
"Gather context" -> "Read changed files fully";
"Read changed files fully" -> "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 FULL content of every changed file (not just diff hunks)
- Identify who uses this code — end users, partner developers, internal consumers
Step 1.5: Triage the Change
Before writing, assess the change's significance:
- Cosmetic/style-only (renames, formatting, whitespace): Keep the review short. Skip "What I'd Kill" and "Taste Check." Focus on whether the cleanup is complete and consistent. Don't write a product manifesto about a formatting change.
- Behavioral change in existing code (bug fix, refactor): Full review. Emphasize whether the fix improves or degrades the developer experience.
- New feature/endpoint/API surface: Full review. This is where Jobs would spend the most time — does this earn its place in the product?
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.
- 12d ago First seen · 165 lines · 134 tokens per session scan A 6d06a509640d
jobs-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 2,562 once invoked, about $0.0007 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
review
Adversarial design review of a System Design Doc. Interrogates the staff questions, finds the cost-explosion and failure risks, returns a verdict. Sensors and evals gate.
ln-75-architecture-diagram-builder
Creates current or target architecture diagrams as the primary deliverable. Not for UI design, architecture audits, or invented structure.
liquid-glass
Implement Liquid Glass design using .glassEffect() API for iOS/macOS 26+. Covers SwiftUI, AppKit, UIKit, and WidgetKit. Use when creating modern glass-based UI effects.
app-icon-generator
Generates an app icon for macOS or iOS — a fast CoreGraphics placeholder and/or flat layered source art to finish in Icon Composer (the Liquid Glass / iOS 26+ standard). Produces appearance variants (light/dark/tinted) and installs into the asset catalog. Use when the user wants to create, generate, iterate, or update…
preview-data-generator
Generate sample data and a multi-variant.
animation-patterns
SwiftUI animation patterns including springs, transitions, PhaseAnimator, KeyframeAnimator, SF Symbol effects, scroll-driven effects, mesh gradients, text renderers, and shader effects. Use when implementing, reviewing, or fixing animation or visual-effect code on iOS/macOS.