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 glebis/humane-agentic-design --skill layout-rulesgit clone --depth 1 https://github.com/glebis/humane-agentic-designWrote 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/glebis/humane-agentic-design/layout-rules)<a href="https://agentmods.dev/skills/glebis/humane-agentic-design/layout-rules"><img src="https://agentmods.dev/badge/skills/glebis/humane-agentic-design/layout-rules/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/glebis/humane-agentic-design/layout-rules"><img src="https://agentmods.dev/badge/skills/glebis/humane-agentic-design/layout-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00135 | $0.01323 |
| Opus 5.5 | $0.00054 | $0.00529 |
| Sonnet 5.5 | $0.00027 | $0.00265 |
| Haiku 4.5 | $0.00014 | $0.00132 |
Grade A, and why
layout-rules 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layout Rules
Announce at start: "I'm using the humane:layout-rules skill to check this layout against the defect avoid-list."
A defect-class avoid-list for tool/dashboard UIs. Every rule is a bug or design smell actually caught in a real build-and-audit cycle — treat them as hard constraints, not suggestions.
Usage
- Read the full ruleset:
layout-design-rules.md, bundled next to this file (single source of truth — do not duplicate it here). - Before designing: apply sections «Structure & hierarchy», «Color & contrast», «De-slop» as constraints in the design plan. Say explicitly which rules shaped the plan.
- While building: enforce «Footers, metrics, copy», «Tables & lists», «State & navigation», «Interaction correctness», «Accessibility & touch», «i18n & theming».
- After building: run the post-build checklist below; screenshot-test in a real browser (rule 29) on both themes and on an empty/minimal dataset (rule 30).
Post-build checklist (the ones most often violated)
- Zero left-border accent rails (rule 1); zero eyebrow caps-labels (rule 2)
- Third heading level actually exists and is distinguishable (rule 3)
- Every verdict/summary line adds a conclusion or names a linked entity (rules 5, 8)
- Every metric is informative or clickable-to-filter (rules 6–7)
- Tables sortable + filterable, tabular-nums (rule 10)
- Faintest text token clears 4.5:1 on both themes (rule 12)
- Every app location has a URL; reload restores it exactly (rule 16)
-
[hidden]{display:none}for every display-classed component; close/reset logic before early returns in delegated handlers (rules 18–19) - SVG interactives: focus ring, keyboard activation, tap-tooltips (rules 22–23)
- Both locales key-parity if i18n exists (rule 27)
Conflict precedence
The user's explicit words > this ruleset > project's existing system > personal taste. If a rule conflicts with an existing design system in the repo, flag it, don't silently rewrite.
What ships with it
2 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.
- 1mo ago Changed · +3 lines ff3afbf41eae
- 2mo ago First seen · 84 lines · 135 tokens per session scan A 84684bf5d128
layout-rules is a skill published in the GitHub repository glebis/humane-agentic-design (41 stars, last pushed 24d ago), licensed MIT. It adds 135 tokens to every session and 1,323 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 2026-08-30.
layout-rules compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| layout-rulesglebis/humane-agentic-design | Skill | 41 | 24d ago | MIT | A | 135 | Claude Code, Codex |
| ui-forgeDNM03/ui-forge | Skill | 6 | 1mo ago | MIT | A | 65 | Codex |
| popular-web-designsNousResearch/hermes-agent | Skill | 262k | yesterday | MIT | A | 23 | Claude Code, Codex |
| web-prototypenexu-io/open-design | Skill | 107k | yesterday | Apache-2.0 | A | 59 | Claude Code, Codex |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 49k | 3d ago | MIT | A | 34 | Claude Code |
| web-prototype-taste-brutalistnexu-io/open-design | Skill | 107k | yesterday | Apache-2.0 | A | 70 | Claude Code, Codex |
| web-prototype-taste-softnexu-io/open-design | Skill | 107k | yesterday | Apache-2.0 | A | 69 | Claude Code, Codex |