Borrowing it
Nothing to install: this file belongs to sapiom/sapiom-js. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sapiom/sapiom-js/main/.claude/skills/establishing-studio-design-clarity/SKILL.mdgit clone --depth 1 https://github.com/sapiom/sapiom-jsWrote 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/sapiom/sapiom-js/establishing-studio-design-clarity)<a href="https://agentmods.dev/skills/sapiom/sapiom-js/establishing-studio-design-clarity"><img src="https://agentmods.dev/badge/skills/sapiom/sapiom-js/establishing-studio-design-clarity.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 12 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.01054 |
| Opus 5 | $0.00048 | $0.00527 |
| Sonnet 5 | $0.00019 | $0.00211 |
| Haiku 4.5 | $0.00010 | $0.00105 |
Grade A, and why
establishing-studio-design-clarity 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Establishing Studio design clarity
Overview
Before you change Agent Studio / harness UI, establish what you're building from. Same rule as its authoring sibling: search first; then — only if you can't find it — ask before you build. Never ask before searching; never invent a visual or product direction in a vacuum. This skill is deliberately thin — it encodes where the Studio's design lives and the ask-default, not how to search.
The Studio's design source is @sapiom/design-system, resolved through the harness build seam
(the branded package when installed, else the committed ds-neutral token mirror — see
web/vite.config.ts). Its hygiene rule already exists: harness CLAUDE.md #6 — never redefine a
design-system token; read values with var(). A local snapshot of token values is drift the moment
the source moves.
The intake — run it before you implement
1. Classify the change: design work (new/restyled surface, "make it better/redesign") → full · hotfix → light · experiment → lightest.
2. Find what you're building from — search before you ask, in order:
- The ask — the ticket/PR for a design link, screenshot, or named reference.
- Existing patterns — grep
packages/harness/web/src(andpackages/harness-desktop/src/renderer) for the same surface; a sibling component usually solved it. Match its anatomy. - The tokens — the design-system seam:
@sapiom/design-systemorpackages/harness/web/src/styles/ds-neutral/tokens.css(the committed mirror). Read viavar(); do not redefine or re-snapshot values.
3. Verdict — and the ask-rule:
- Found a clear design or an existing surface to match → proceed; conform per harness
CLAUDE.md#6 (tokens viavar(), no local redefinition). Surface only the one real judgment call, after. - Design work, and after searching no clear design or intent → stop and ask 1–2 targeted questions before building. Not proceed-on-a-default-and-notify. If the ask is a genuinely new, unspecified design, capture it as a written design doc first (so it isn't consumed verbally). On an unattended/automated run (no human to answer), post the question on the ticket/PR and stop — asking is not permission to build; if something must ship, build the smallest precedent-anchored version and label it as needing design sign-off.
- Hotfix or experiment with minor ambiguity → proceed with a precedent-anchored default; flag what you assumed.
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 · 60 lines · 96 tokens per session scan A 5870054cd324
establishing-studio-design-clarity is a skill published in the GitHub repository sapiom/sapiom-js (19 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 1,054 once invoked, about $0.0005 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 2026-08-30.
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 $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.