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-exploregit 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-explore)<a href="https://agentmods.dev/skills/vidhunnan/agentic-skills/design-explore"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-explore/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-explore"><img src="https://agentmods.dev/badge/skills/vidhunnan/agentic-skills/design-explore.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 | $0.03858 |
| Opus 5 | $0.00069 | $0.01929 |
| Sonnet 5 | $0.00028 | $0.00772 |
| Haiku 4.5 | $0.00014 | $0.00386 |
Grade A, and why
design-explore 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 9d 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design-explore
Produces the thing that's missing between a written direction and a built screen: options you can actually look at. Three directions, each committed to a different structural idea, laid out so the choice is made by eye rather than by reading three paragraphs describing three things that don't exist yet.
The failure this is built against is specific and extremely common. Asked for "a few options", a model produces one layout in three colourways, describes them in confident prose, and calls it an exploration. Nothing was explored: the same structural decision was made three times and painted differently. A real exploration commits each direction to a different bet, and makes the bets visible.
Why this skill is allowed to generate at all
Every other skill in this territory is restricted to interview, record, structure, check by ADR 0021. This one generates, which ADR 0022 permits — into the explorations tier only, under three conditions that all must hold. They are not framing; they are the reason the skill is permitted:
- A written visual intent exists first. No language doc, no generation. Step 2 is a gate, not a lookup.
- The artifacts are candidates, never the record. They are material to look at and reject. Nothing here is evidence that anything was decided or shipped.
- The verdict belongs to another skill.
exploration-logrecords what was kept or killed;design-decisionsrecords why. Step 8.
Drop any one of the three and ADR 0021's original objection applies again — and the fix is to restore the condition, not to proceed anyway.
Four rules govern the work itself:
- Never generate against nothing. With no stated visual intent, what comes out
is the median of everything the model has seen — competent and anonymous. Read the
design-languagedoc first, or run a compressed version of that interview. This is the whole difference between exploration and autocomplete. - Distinct on structure, not on hue. Every direction is assigned a named axis it commits to, and the axis is stated in the matrix. Two directions may not differ only in colour.
- No strawmen. The classic three-option failure is two real directions and one obviously-worse filler that exists to make the favourite win. If you can't argue for a direction, it doesn't ship as one of the three.
- The answer may be a merge. Directions are lettered so "take B's structure with C's type" is a sayable sentence. Say so out loud at the end — the best outcome here is frequently a combination, not a winner.
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.
- 9d ago First seen · 311 lines · 138 tokens per session scan A e4aeec5120ac
design-explore 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 3,858 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.