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 ssheleg/super-ux --skill ux-auditgit clone --depth 1 https://github.com/ssheleg/super-uxWrote 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/ssheleg/super-ux/ux-audit)<a href="https://agentmods.dev/skills/ssheleg/super-ux/ux-audit"><img src="https://agentmods.dev/badge/skills/ssheleg/super-ux/ux-audit/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/ssheleg/super-ux/ux-audit"><img src="https://agentmods.dev/badge/skills/ssheleg/super-ux/ux-audit.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 | $0.00085 | $0.04453 |
| Opus 5 | $0.00043 | $0.02227 |
| Sonnet 5 | $0.00017 | $0.00891 |
| Haiku 4.5 | $0.00009 | $0.00445 |
Grade A, and why
ux-audit 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 2d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ux-audit — Scenario Audit Loop
Part of super-ux — see system-map.md for the whole pipeline and the four sync rules. Start any audit by running the linter (
python3 docs/ux/lint.py) — it catches structural drift for free before the code-tracing passes.
Verify that the code actually delivers every scenario in
docs/ux/scenarios.md: every step reachable, every button present, every
state handled, every error honest. Output: a versioned report in
docs/ux/audits/ plus updated audit statuses in the base.
Format contract: scenario-format.md (ux-contract v4) — report structure, verdicts (PASS / PARTIAL / FAIL / BLOCKED), severities.
Precondition: docs/ux/scenarios.md exists. If it doesn't, stop and run
the ux-scenarios skill first — there is nothing to audit against. The
opt-out is spoken: an operator saying "no scenarios" / «без сценариев»
declines the scenario route — review what exists without the base and state
that in the report.
Full context: when docs/ux/foundation.md exists, audit each scenario
WITH its chain — load the traced story's acceptance criteria (Given/When/
Then) as additional checks, and note whether the implementation actually
serves the job and journey stage, not just renders the elements. A flow
whose buttons all exist but whose job outcome is unreachable is PARTIAL at
best. When docs/ux/flows.md exists, also verify the code implements the
flow diagram: every node reachable, every edge (including error edges)
wired, screen states from the flow's table present — unimplemented
nodes/edges are findings on the traced scenarios.
Copy scope (copy)
Single-pass, and the twin of python3 docs/brand/lint.py: the linter proves
the mechanical half of the brand pack, this judges the half that needs a
reader. Requires docs/brand/voice.md; without a recorded pack there is
nothing to judge against except taste, so route to /brand-init instead.
What ships with it
19 files 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.
- references/ai-tells.md 14 KB
- references/best-practices-index.md 25 KB
- references/best-practices.md 170 KB
- references/brand-contract.md 17 KB
- references/channel-playbooks.md 5.7 KB
- references/component-guidelines.md 5.3 KB
- references/figma-integration.md 10 KB
- references/figma-structure.md 5.4 KB
- references/localization.md 5.2 KB
- references/marketing-copy.md 7.0 KB
- references/practice-selection.md 12 KB
- references/scenario-format.md 43 KB
- references/seo-aeo-safety.md 6.4 KB
- references/store-copy.md 5.1 KB
- references/surface-registers.md 8.5 KB
- references/system-map.md 8.3 KB
- references/ux-design-principles.md 13 KB
- references/visual-identity.md 7.5 KB
- references/voice-packs.md 16 KB
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.
- 2d ago Changed · +3 lines 617713c7a76c
- 4d ago Changed · +32 lines dc2a6d920822
- 9d ago First seen · 278 lines · 85 tokens per session scan A b47ff2ae1885
ux-audit is a skill published in the GitHub repository ssheleg/super-ux (3 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 4,453 once invoked, about $0.0004 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
accessibility-per-component
Run an accessibility audit on a specific design system component. Trigger when someone says: accessibility check, a11y audit, WCAG compliance, is this accessible, check accessibility, does this meet WCAG, screen reader support, keyboard navigation check, or anything about auditing the accessibility of a specific…
schema-validator
Validate token files against DTCG 2025.10, Style Dictionary, or custom schemas. Trigger when someone says: validate token JSON, check my token files for errors, schema validation for tokens, are my token files valid, DTCG compliance check, validate token format, or anything about checking whether token files are…
flow-checker
Run preflight and postflight checklists against UX flows before you design and before you ship. Covers onboarding, forms, pricing, dashboards, and empty states. Returns structured findings with severity and smell linkage. Requires uxuiprinciples.com API Access (pro tier).
wireframing
Low/high fidelity wireframes, user flows, information architecture, prototyping techniques, and design iteration processes.
product-design
Design de produto nivel Apple — sistemas visuais, UX flows, acessibilidade, linguagem visual proprietaria, design tokens, prototipagem e handoff. Cobre Figma, design systems, tipografia, cor, espacamento, motion design e principios de design cognitivo.
prototype-designer
A guide for designing interactive prototypes and user flows before building the final product. A prototype is a clickable model used to explore how an interface should work.