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 connerkward/deterministic-design-skill --skill design-spatialgit clone --depth 1 https://github.com/connerkward/deterministic-design-skillWrote 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/connerkward/deterministic-design-skill/design-spatial)<a href="https://agentmods.dev/skills/connerkward/deterministic-design-skill/design-spatial"><img src="https://agentmods.dev/badge/skills/connerkward/deterministic-design-skill/design-spatial/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/connerkward/deterministic-design-skill/design-spatial"><img src="https://agentmods.dev/badge/skills/connerkward/deterministic-design-skill/design-spatial.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 | $0.00000 | $0.04445 |
| Opus 5.5 | $0.00000 | $0.01778 |
| Sonnet 5.5 | $0.00000 | $0.00889 |
| Haiku 4.5 | $0.00000 | $0.00445 |
Grade A, and why
design-spatial 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.
This is a copy
100% identical to design-spatial — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design — spatial composition
A model cannot trust its own UI output. Everything else follows from two failures.
1. It can't see what it made
UI is generated as a token stream, never as pixels — so the model cannot perceive collisions, overlap, imbalance, or broken spacing. It will write a headline that runs into the hero image and have no idea.
Render it and judge the image, not the code. Serve with any static server (e.g. python3 -m http.server or npx serve) and screenshot headless via Playwright. Screenshot at a few widths.
Critique with fresh eyes — not your own. Grading your own output rationalizes it; the builder looks at its overlapping headline and calls it fine (this is exactly how a real collision shipped in testing). Use a separate judge — a subagent that did not write the page — and tell it to hunt for what's wrong: collisions, edge tangents, ragged alignment, lopsided weight, no clear focal point, breaks at some width. Fix, re-render, re-judge.
2. Its first idea is the average
Whatever it produces first is the mean of its training data — and there is more than one mean:
- the generic-AI mean: Inter, purple-on-white gradients, centered single column, three equal cards;
- the designer-trend mean: oversized condensed caps, dark-mode + grain, monospace "vibes" microtext, sticker badges.
Landing on the second isn't taste — it's a more flattering average, which is why it slips past. Treat your first instinct as the mean and deviate deliberately — toward this product's specific world (use design-thinking's domain / color-world / signature as the direction), not toward another trend. If the result could be any startup, you shipped the mean.
3. So don't prescribe a style
Any fixed rule — a 12-col grid, an 8-point scale, "mono = data" — becomes next cycle's mean, and a blind model executes it into collisions anyway. Prescribe the process, not the look: see it with fresh eyes, and push off the average toward the domain. Taste supplies the direction (design-thinking / design-philosophy); this skill only insists you look and don't ship the mean.
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.
- 1mo ago First seen · 256 lines · 0 tokens per session scan A 4cf938a363a2
design-spatial is a skill published in the GitHub repository connerkward/deterministic-design-skill (4 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,445 tokens. A static security scan graded it A with 0 findings. It is 100% identical to design-spatial, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
design-spatial
Spatial composition and layout for frontend design. Load with design when composing pages/dashboards/components, or whenever generated UI looks off — overlapping/colliding elements, weak hierarchy, or generic ("looks like every startup site"). The core idea: a model can't trust its own layout, so render it, critique…
design-system
Mechanical implementation invariants for frontend design: token architecture, typography hierarchy, loading order, FOUT prevention, chrome stability, motion timing, color semantics. Use with design when building components, pages, or design systems. (Aesthetic direction lives in design-thinking; anti-trend/anti-slop…
ckw-design
Entry point for frontend design. Use WHENEVER building or touching the look of any web UI — components, pages, dashboards, landing pages, React/Vue/HTML-CSS — and whenever the user says "make this look better/nicer", "fix the spacing/layout", or mentions styling, color, typography, fonts, responsive design, polish, or…
design-thinking
Direction and intent for frontend design. Use with design when defining purpose, tone, domain, color world, and review bar; includes cross-domain lens from cinema, architecture, marketing, UX, automotive, industrial design.
design-ux
UX / usability audit — heuristic evaluation of INTERACTIVE UIs (not just visual polish). Load with design when a UI "feels off", "sucks to use", is hard to learn, needs an instruction wall, or before shipping an interactive tool/editor/app. Scores the RENDERED UI against Nielsen's 10 + interaction heuristics via a…
design-philosophy
Visual philosophy and art-direction for frontend. Use when creating high-concept work, campaigns, or when the user asks for a visual philosophy, manifesto, or unmistakable art-like aesthetic.