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 GalaxyRuler/Galactic-skills --skill distinctive-design-gatesgit clone --depth 1 https://github.com/GalaxyRuler/Galactic-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/galaxyruler/galactic-skills/distinctive-design-gates)<a href="https://agentmods.dev/skills/galaxyruler/galactic-skills/distinctive-design-gates"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/distinctive-design-gates/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/galaxyruler/galactic-skills/distinctive-design-gates"><img src="https://agentmods.dev/badge/skills/galaxyruler/galactic-skills/distinctive-design-gates.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 | $0.00078 | $0.00635 |
| Opus 5.5 | $0.00031 | $0.00254 |
| Sonnet 5.5 | $0.00016 | $0.00127 |
| Haiku 4.5 | $0.00008 | $0.00064 |
Grade A, and why
distinctive-design-gates 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 2mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distinctive Design Gates
Overview
The user consistently rejects generic, AI-default design: template card grids, stock gradient heroes, interchangeable SaaS aesthetics. Run these deny-gates before presenting any design. A design that fails a gate is not shown — iterate first. This is a standing rule.
When to use
Use this when:
- Presenting any web/UI design, mockup, landing page, or redesign.
- Iterating after a design rejection.
- Reviewing design work another agent produced before it reaches the user.
Deny-gates (all must pass before presenting)
- Not generic
- Would this design be recognizable among ten AI-generated sites for the same brief? If it could be anyone's site, it fails.
- Default-stack tells (uniform card grids, gradient hero + three feature columns, stock icon rows, purple-on-dark SaaS defaults) fail unless deliberately subverted.
- Meaningfully different from rejected iterations
- Each new iteration must change layout structure AND type system AND visual concept relative to rejected ones. A recolor or reskin of a rejected skeleton fails.
- Keep a written list (in the session or a scratch file) of rejected directions and what was rejected about each; check new work against it before presenting.
- Full pages, not fragments
- Present complete rendered pages, top to bottom. Cropped sections and isolated components hide the overall impression the user judges by.
- Identity preserved
- The user's stated identity, content requirements, and multi-facet positioning must survive the redesign. A beautiful page that erases required content fails.
- Grounded direction
- Anchor each direction in distinctive real-world references (found via online search when needed), not in the model's default aesthetic.
Workflow
- Before designing, restate the identity/content constraints and the list of previously rejected directions.
- Choose a distinctive concept and reference points; note what makes it non-generic.
- Build the full page(s).
- Run the five gates. Fail → iterate before showing anything.
- Present with a one-line statement of the concept and how it differs from the last iteration.
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.
- 2mo ago First seen · 60 lines · 78 tokens per session scan A 3049cd242861
distinctive-design-gates is a skill published in the GitHub repository GalaxyRuler/Galactic-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 78 tokens to every session and 635 once invoked, about $0.0003 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 2026-09-06.
distinctive-design-gates compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| distinctive-design-gatesGalaxyRuler/Galactic-skills | Skill | 5 | 2mo ago | MIT | A | 78 | Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | today | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |