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 mxyhi/ok-skills --skill unslopgit clone --depth 1 https://github.com/mxyhi/ok-skillsWrote 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/mxyhi/ok-skills/unslop)<a href="https://agentmods.dev/skills/mxyhi/ok-skills/unslop"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/unslop/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/mxyhi/ok-skills/unslop"><img src="https://agentmods.dev/badge/skills/mxyhi/ok-skills/unslop.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 | $0.00152 | $0.07239 |
| Opus 5.5 | $0.00061 | $0.02896 |
| Sonnet 5.5 | $0.00030 | $0.01448 |
| Haiku 4.5 | $0.00015 | $0.00724 |
Grade A, and why
unslop 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 9d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unslop
unslop was created by Damir Sokolovsky (@heydamir), who started the Unslopping series on X. It is licensed under CC BY 4.0, so keep this credit in any copy or adaptation.
Vibecoded UI fails in the same predictable ways. Every surface glows, every label has an emoji, spacing is whatever the model typed that day, and the copy shouts. Unslopping fixes the craft and keeps the product. The features, content and order of sections stay. What changes is that every size, color, word and image becomes deliberate.
Removing slop is only half the job. A screen that is clean but could belong to any product is the next template. Every run ends with a screen that only this product could have.
The difference between slop and craft is where the richness goes. Slop spreads color and effects over the chrome, the backgrounds, buttons, borders and labels. Craft keeps the chrome quiet and puts the richness into one or two moments of content that people remember, like a rendered object, a beautiful chart or an image from the product's world.
Work like a designer doing a redline pass, one layer at a time, across the whole screen.
What good looks like
- One bright element. Each screen has one polished thing that carries the color and the craft, a rendered object, a painted scene or a rich chart. Everything around it is quiet, so it reads instantly.
- Quiet chrome. Navigation, buttons and text use the tinted neutrals and one accent. Nothing glows, nothing competes with the bright element.
- A clear idea. You can say in one sentence what the visual shows and why it belongs to this product.
- Text on calm space. The headline sits on a part of the image or layout that was left empty for it, short and specific, with one primary and one secondary action and nothing stacked under them.
- Real product, real material. Previews look like the real app with plausible data, and objects look like real things with weight, light and shadow.
Which visual styles tend to work, and which fail, is in references/visuals.md. Finished examples to learn from are in references/refs.md, and code treatments like drawing an image in glyphs are in references/effects.md.
What ships with it
13 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.
- agents/openai.yaml 196 B
- references/effects.md 4.8 KB
- references/refs.md 2.4 KB
- references/refs/beacon-engraving.webp 556 KB
- references/refs/meadow-3d.webp 280 KB
- references/refs/story-dashboard-frames.webp 183 KB
- references/refs/unslop-dashboard-after.webp 73 KB
- references/refs/unslop-hero-after.webp 218 KB
- references/signs.md 6.9 KB
- references/tokens.md 6.3 KB
- references/visuals.md 8.1 KB
- scripts/snapshot.mjs 6.4 KB runs code
- scripts/story.mjs 23 KB runs code
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.
- 9d ago First seen · 234 lines · 152 tokens per session scan A 9e49b2ff7643
unslop is a skill published in the GitHub repository mxyhi/ok-skills (516 stars, last pushed 10d ago), licensed Apache-2.0. It adds 152 tokens to every session and 7,239 once invoked, about $0.0006 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 2026-11-08.
unslop compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unslopmxyhi/ok-skills | Skill | 516 | 10d ago | Apache-2.0 | A | 152 | Codex |
| frontend-ui-engineeringaddyosmani/agent-skills | Skill | 119k | 4d ago | MIT | A | 58 | Claude Code |
| impeccablesjarmak/coding-agent-workflows | Skill | 7 | 23d ago | MIT | A | 57 | Claude Code, Codex |
| shadcnuiG1Joshi/Agent-Skills | Skill | 15 | 1mo ago | MIT | A | 42 | Claude Code, Codex |
| frontend-ui-engineeringhelderberto/agent-skills | Skill | 20 | 23d ago | MIT | A | 69 | Claude Code |
| bootstrapG1Joshi/Agent-Skills | Skill | 15 | 1mo ago | MIT | A | 37 | Claude Code, Codex |
| tailwindcssG1Joshi/Agent-Skills | Skill | 15 | 1mo ago | MIT | A | 33 | Claude Code, Codex |