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/PMDevSolutions/Aureliusnpx agentmods add commands/pmdevsolutions/aurelius/export-design-systemWrote 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/commands/pmdevsolutions/aurelius/export-design-system)<a href="https://agentmods.dev/commands/pmdevsolutions/aurelius/export-design-system"><img src="https://agentmods.dev/badge/commands/pmdevsolutions/aurelius/export-design-system/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/commands/pmdevsolutions/aurelius/export-design-system"><img src="https://agentmods.dev/badge/commands/pmdevsolutions/aurelius/export-design-system.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 | $0.00000 | $0.01084 |
| Opus 5.5 | $0.00000 | $0.00434 |
| Sonnet 5.5 | $0.00000 | $0.00217 |
| Haiku 4.5 | $0.00000 | $0.00108 |
Grade A, and why
export-design-system 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/export-design-system — Export Components as a Publishable Library
Export the generated components and design tokens from this project as a publishable pnpm workspace with a framework-agnostic token package and a framework-specific component library (Vite library mode for web, tsc for React Native).
Input
$ARGUMENTS — optional flags forwarded to the export script. Common patterns:
- (none) — default: detect framework from
build-spec.json, scope frompackage.json, output todist/design-system/. --scope @acme— override the npm scope.--output packages/design-system— pick a different output location.--framework vue— override detected framework.--dry-run— preview without writing.--force— overwrite existing output dir.--json— machine-readable summary.
Preconditions
This command requires:
design-tokens.lock.jsoninsrc/styles/or project root (produced by thedesign-token-lockskill or any of the/build-from-*pipelines).- At least one component in
src/components/(or pass--components-dir). - Framework discoverable via
build-spec.json(outputTarget),package.jsondeps, or--frameworkflag.
If any precondition is missing, stop and tell the user which one and how to fix it (run a build pipeline, pass a flag, etc.) — do not attempt to repair the project automatically.
Steps
1. Sanity check inputs
Run a quick detection pass before invoking the skill:
test -f src/styles/design-tokens.lock.json || test -f design-tokens.lock.json
ls src/components 2>/dev/null | head -1
If lockfile is missing, surface the error and recommend running /build-from-figma, /build-from-canva, or /build-from-screenshot first.
2. Confirm scope and output (only if user did not pass them)
If the user did not provide --scope or --output, ask them once via AskUserQuestion:
- Scope: "What npm scope should the packages publish under? (e.g.
@acme)" — default to the value detected from the project'spackage.json, or@my-app. - Output dir: offer
dist/design-systemas the default and let them confirm or override.
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 · 111 lines · 0 tokens per session scan A 29b55f7644df
export-design-system is a command published in the GitHub repository PMDevSolutions/Aurelius (9 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,084 tokens. 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 2026-09-04.
Other commands, from other repositories
dashboard-layout
Design and build a complete dashboard layout — sidebar navigation, KPI cards, chart areas, data tables, filter bar, and responsive behavior. Outputs production-ready HTML/CSS.
sheleg-design
Apply SHELEG Design to the current landing, hero, motion or product UI task.
figma-start
A command that prepares a designer's review branch from a developer's GitHub pull request. A pull request is a proposed set of code changes, and a branch is a separate line of project history.
handoff
A handoff command that creates a pull request from a designer's working branch to the developer's branch after design changes are ready for review. A pull request is a request to inspect and merge code changes.
figma-apply
A command that applies changes from a Figma design file to the current design branch, then commits, pushes, and checks the project build. Figma is a tool for creating and sharing interface designs.
/a11y-audit
Auditoría de accesibilidad WCAG 2.2 completa con escaneo de HTML/componentes. Detecta: alt text faltante, problemas de contraste, navegación por teclado, etiquetas ARIA, gestión de focus, jerarquía de encabezados, etiquetas de formularios. Genera reporte accionable con instrucciones de remediación.