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 avanturer/claude-bestpractice --skill landing-not-slopgit clone --depth 1 https://github.com/avanturer/claude-bestpracticeWrote 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/avanturer/claude-bestpractice/landing-not-slop)<a href="https://agentmods.dev/skills/avanturer/claude-bestpractice/landing-not-slop"><img src="https://agentmods.dev/badge/skills/avanturer/claude-bestpractice/landing-not-slop/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/avanturer/claude-bestpractice/landing-not-slop"><img src="https://agentmods.dev/badge/skills/avanturer/claude-bestpractice/landing-not-slop.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 | $0.00034 | $0.01170 |
| Opus 5 | $0.00017 | $0.00585 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
landing-not-slop 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 11d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Landings that do not read as generated
A page assembled from the defaults reads as generated within two seconds, and the visitor's conclusion is not "this is AI" — it is "this is not a real company". That judgement lands before a single word is read, which is why this is a design problem rather than a copy problem.
The tells below are concrete because "make it look modern" is not actionable and produces the same page every time.
The visual tells, and what to do instead
| Tell | Why it reads as generated | Instead |
|---|---|---|
| Purple-to-blue (or teal-to-indigo) gradient hero | The single most-copied default of the 2023-2025 era | One flat brand colour, or a photograph, or a product screenshot on a plain field |
| Three feature cards, each an icon + 3-word title + 2 lines | The shape a model reaches for when it has nothing specific to say | However many features are real. Two is fine. Show the thing working |
| Generic line-art icons (rocket, lightning, shield, gear) | Chosen for "tech feel", carry zero information | Product screenshots, a number, or nothing |
| Everything centred, everything the same width | No hierarchy means nothing is important | Asymmetry. One thing on the page is biggest, and it is the one that matters |
| Glassmorphism, heavy blur, floating 3D blobs | Peaked in 2022 and now dates a page instantly | Flat surfaces, real borders, one shadow depth |
| Every section fading in on scroll | Motion applied uniformly is decoration, not communication | Motion on one element that rewards attention, or none |
| Emoji as section markers | 🚀 ✨ 💡 in headings is the strongest single tell | Words |
| Dark hero, light body, dark footer | Alternation for its own sake | One background. Change it only where the meaning changes |
The copy tells
- "Seamlessly", "effortlessly", "unlock", "elevate", "supercharge", "revolutionise", "game-changing", "cutting-edge", "robust", "leverage", "empower". Any of these in a headline means the headline says nothing. Delete the word and see if the sentence survives; usually it improves.
- Triads. "Fast, simple, and secure." "Build, ship, and scale." The rule of three is the most obvious rhythm in the training data. Break it — two, or four, or one.
- The em-dash-heavy voice with "It's not just X — it's Y." That construction is a tell on its own now.
- Headlines that describe the category, not the product. "The modern way to manage your finances" describes a category. "See every subscription you forgot about" is a product.
- Testimonials with full names, job titles, and companies that do not exist. Never fabricate one. No testimonials beats invented testimonials — and invented ones are a legal exposure, not just a taste failure.
- Stats with no source. "10x faster" with nothing behind it. Either cite the measurement or cut the number.
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.
- 11d ago First seen · 82 lines · 34 tokens per session scan A e13355902bd9
landing-not-slop is a skill published in the GitHub repository avanturer/claude-bestpractice (2 stars, last pushed 5d ago), licensed MIT. It adds 34 tokens to every session and 1,170 once invoked, about $0.0002 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
design-is
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design…
creo-design-review
Comprehensive UI/UX design review with Playwright. Evaluates responsive design (375-1920px), WCAG AA accessibility, Nielsen's 10 heuristics, component consistency, and visual polish. Trigger keywords: design review, UI review, accessibility audit, responsive check, heuristic evaluation.
creo-ux-competitor
Analyze competitor websites for UX patterns, strengths, and weaknesses. Navigates external URLs, documents UX patterns, evaluates against Nielsen heuristics, and extracts actionable learnings. Trigger keywords: competitor analysis, competitor UX, competitive analysis, benchmark, compare competitors.
excalidraw
Generate Excalidraw diagrams from a compact DSL with brand-resolved colors. Use for boxes/arrows flow diagrams.
svg
Generate SVG diagrams from a compact DSL with brand-resolved colors. Use for charts, flows, and schematic 2D graphics.
creo
Comprehensive design, UX, content, DevOps, and testing toolkit for web applications. Design reviews, UX flow analysis, marketing content, SEO auditing, CI/CD pipelines, test orchestration, performance optimization, and marketing site creation. Triggers on: /creo, design review, UX analysis, marketing content, SEO…