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 vidhunnan/agentic-skills --skill design-setupgit clone --depth 1 https://github.com/vidhunnan/agentic-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/vidhunnan/agentic-skills/design-setup)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/design-setup"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-setup/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/vidhunnan/agentic-skills/design-setup"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-setup.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 | $0.00138 | $0.05822 |
| Opus 5 | $0.00069 | $0.02911 |
| Sonnet 5 | $0.00028 | $0.01164 |
| Haiku 4.5 | $0.00014 | $0.00582 |
Grade A, and why
design-setup 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 8d 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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-setup
Builds a project's design context stack: the folders that make design reasoning survive the person who did it.
Code has git log. Every decision leaves a commit, a diff, a blame line — a poor
record, but a recoverable one. A Figma file is a snapshot of the winner. It does
not hold the problem, the directions that were killed, why the survivor won, what
was traded away, or which details are decisions rather than leftovers. That
reasoning lives in comment threads and one person's memory, and within months it is
gone from both.
Every other design skill — critique, decisions, exploration logs, specs — needs somewhere to write. This is what creates it.
Two principles govern every step, inherited from repo-setup because they are the
same two problems:
- Detect, map, confirm — never impose. If the project already calls it
brand/, then the system tier isbrand/. Canon fills gaps; it does not rename anyone's repo. - Additive only. Never move, rename, delete, or overwrite. Every write is a file that did not exist. If the right answer requires moving files, say so and let the human do it.
The canon
Used only to fill gaps — an existing path always wins (see Step 1).
| Tier | Canonical path | Question it answers | Status |
|---|---|---|---|
| Briefs | design/briefs/ |
What problem are we solving? | proposal — the design PRD |
| Research | design/research/ |
What did we learn? | evidence — observation kept separate from interpretation |
| Explorations | design/explorations/ |
What did we try? | history — includes everything killed |
| Decisions | design/decisions/ |
Why did we choose this? | truth — past tense, append-only |
| Specs | design/specs/ |
What is it, exactly? | spec — pinned to a source version |
| System | design/system/ |
What's reusable? | truth — the system of record |
There is no design changelog tier, deliberately. What shipped is changelog/,
generated from git. A hand-written parallel would be hypothesis wearing the costume
of truth — the exact failure the done-vs-explored rule exists to prevent. If the
user asks for one, say this and point at changelog/.
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.
- 8d ago First seen · 412 lines · 138 tokens per session scan A 1fa93fb008fb
design-setup is a skill published in the GitHub repository vidhunnan/agentic-skills (2 stars, last pushed 3d ago), licensed MIT. It adds 138 tokens to every session and 5,822 once invoked, about $0.0007 per session on Opus 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 2026-08-31.
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.