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 sanky369/vibe-building-skills --skill design-engineer-mindsetgit clone --depth 1 https://github.com/sanky369/vibe-building-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/sanky369/vibe-building-skills/design-engineer-mindset)<a href="https://agentmods.dev/skills/sanky369/vibe-building-skills/design-engineer-mindset"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/design-engineer-mindset/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/sanky369/vibe-building-skills/design-engineer-mindset"><img src="https://agentmods.dev/badge/skills/sanky369/vibe-building-skills/design-engineer-mindset.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 | $0.00145 | $0.01994 |
| Opus 5.5 | $0.00058 | $0.00798 |
| Sonnet 5.5 | $0.00029 | $0.00399 |
| Haiku 4.5 | $0.00015 | $0.00199 |
Grade A, and why
design-engineer-mindset 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Engineer Mindset
Close the gap between what was designed and what ships: implement designs exactly — real values, real timing, real physics — while treating the browser's rendering pipeline as part of the design material. The prime directive: fidelity is non-negotiable and measurable. "Approximately the mockup" is a bug; every deviation is either justified in writing or fixed. Deliver the implementation plus a fidelity report; never eyeball-and-ship.
When to use / when not to
Use for: design-to-code implementation, closing design/implementation drift, setting up design tokens as code, fixing stuttering animations at the rendering level (layout thrashing, non-compositor properties), frame-budget work.
Hand off instead when the real need is:
- Choosing durations/easings and motion vocabulary →
skills/frontend-design/interaction-physics(that skill decides the spec; this one implements it faithfully and keeps it at 60fps) - Network/perceived latency, Core Web Vitals →
skills/frontend-design/performance-optimization - Structuring the components you're about to build →
skills/frontend-design/component-architecture - Inventing the design itself (no mockup exists) →
skills/frontend-design/design-foundationand the visual-layer skills
Step 0 — Inspect design and codebase, then ask only what's left
- Extract exact values from the design source: spacing, sizes, radii, colors, shadows, type styles, animation durations/easings. If it's a Figma link and Figma tooling is available, pull real values; from a screenshot, measure and mark measured values as approximations in the fidelity report.
- Inspect the code side: existing token system (CSS variables, Tailwind theme, styled-system)? Map every design value to an existing token first; list values with no token as either new tokens or spec deviations to raise.
- Detect the design's underlying system: are spacings multiples of 8 (or 4)? A consistent elevation scale? Duration pattern? Implementing the system beats transcribing pixel values.
- Check rendering hygiene of code you'll touch: grep for animations on
width/height/top/left/margin, interleaved DOM reads/writes in handlers, scroll handlers doing layout reads.
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.
- 2mo ago First seen · 112 lines · 145 tokens per session scan A 06ef73c7246b
design-engineer-mindset is a skill published in the GitHub repository sanky369/vibe-building-skills (31 stars, last pushed 3mo ago), licensed MIT. It adds 145 tokens to every session and 1,994 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 2026-08-30.
design-engineer-mindset compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-engineer-mindsetsanky369/vibe-building-skills | Skill | 31 | 3mo ago | MIT | A | 145 | Claude Code, Codex |
| planjeremylongshore/tons-of-skills-marketplace | Skill | 2.9k | yesterday | MIT | A | 144 | Claude Code |
| prototypevinvcn/mattpocock-skills-zh-CN | Skill | 5.6k | 9d ago | MIT | A | 39 | Claude Code, Codex |
| data-visualization-expertroedyrustam/vibes-plug | Skill | 121 | yesterday | MIT | A | 38 | Cursor |
| design-system-architectroedyrustam/vibes-plug | Skill | 121 | yesterday | MIT | A | 43 | Cursor |
| ephemeral-generative-ui-architectroedyrustam/vibes-plug | Skill | 121 | yesterday | MIT | A | 47 | Cursor |
| prototypedevcxl/mattpocock-skills-zh | Skill | 530 | 3d ago | MIT | A | 39 | Claude Code, Codex |