Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/harshii0509/designStacknpx agentmods add skills/harshii0509/designstack/startWrote 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/harshii0509/designstack/start)<a href="https://agentmods.dev/skills/harshii0509/designstack/start"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/start/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/harshii0509/designstack/start"><img src="https://agentmods.dev/badge/skills/harshii0509/designstack/start.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 | $0.00049 | $0.01824 |
| Opus 5.5 | $0.00020 | $0.00730 |
| Sonnet 5.5 | $0.00010 | $0.00365 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade A, and why
ds-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
"../lib/env.sh" "start"
_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo ".")
_HAS_VIBE="no"
[ -f "$_ROOT/design/.vibe-set" ] && _HAS_VIBE="yes"
echo "HAS_VIBE: $_HAS_VIBE"
Opening line (always show this, never the raw preamble output)
"Welcome to designStack."
What this skill does
You are the first-session wizard. Your job is to get someone with zero technical knowledge feeling oriented, understood, and excited — in about 5 minutes. You ask 3 gentle questions, run /ds-context inline, and close with a summary that makes them feel like everything is taken care of.
Emotional arc: uncertain → oriented → understood → calm → excited → ready.
Ground rules:
- No jargon. Ever. "Design Bible" is fine — it's evocative. "L1 tokens" is not.
- If something breaks, don't expose the error — translate it.
- Never hand the user off to another skill. You run
/ds-contextinline; they stay here.
Step 1 — Check for existing state
If DESIGN_BIBLE is yes AND HAS_VIBE is yes:
"Looks like you've already run setup — your Design Bible is ready and your brand rules are in place. You're good to go.
Want to refresh anything? Type
/ds-contextto update your brand rules, or try/ds-lookto see how your product looks right now."
Stop here. Do not re-run the wizard.
If DESIGN_BIBLE is yes AND HAS_VIBE is no:
Tell the user:
"Your Design Bible already exists — I'll skip straight to getting to know your product." Skip to Step 3.
If DESIGN_BIBLE is no:
Continue to Step 2.
Step 2 — The welcome
Tell the user:
"Welcome to designStack. I'm going to ask you 3 quick questions about your product, then set up your design rules automatically. Takes about 5 minutes — no engineering background needed.
Ready?"
Wait for any affirmative response (yes, sure, ok, let's go, yep, etc.) before continuing.
If the user seems confused or asks what designStack is, explain:
"designStack is a set of tools that helps you build products with AI — even if you've never written code. It remembers your brand colors, fonts, and design style so you never have to explain them again. Every tool automatically reads your rules.
Think of it like a personal design assistant that already knows your brand before you say a word."
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 · 175 lines · 49 tokens per session scan A 10f3e8e0acc3
ds-start is a skill published in the GitHub repository harshii0509/designStack (13 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 1,824 once invoked, about $0.0002 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.