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 Tradebaas/Groundwork --skill designgit clone --depth 1 https://github.com/Tradebaas/GroundworkWrote 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/tradebaas/groundwork/design)<a href="https://agentmods.dev/skills/tradebaas/groundwork/design"><img src="https://agentmods.dev/badge/skills/tradebaas/groundwork/design/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/tradebaas/groundwork/design"><img src="https://agentmods.dev/badge/skills/tradebaas/groundwork/design.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 | $0.00106 | $0.01709 |
| Opus 5.5 | $0.00042 | $0.00684 |
| Sonnet 5.5 | $0.00021 | $0.00342 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
design 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 16d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
design: nothing ships looking or sounding like a default
docs/DESIGN.md sections 1 and 2 and docs/design/VOICE.md carry the durable principles and the
owner's standing taste. DESIGN.md section 3 is written from the built world, after the finish
review (step 4), never before: a rulebook written ahead of the build gets defended against reality
instead of describing it. docs/PRODUCT.md beside DESIGN.md holds what the brief does not own:
platform, brand commitments, evidence on hand, accessibility needs. A fact that stands in both
files will disagree with itself later, so PRODUCT.md points at the brief for scope, users and
purpose.
No DESIGN.md or VOICE.md in this project? Say so, ask the two questions in step 1, and write both files from the answers before any interface work; a project without a design system gets one the first time it needs one.
1. Ask the owner: only what is theirs
- Brand reality: existing logo, colors, fonts, brand guide? If yes, that is binding: collect
the files into
docs/design/reference/and carry them as a brand commitment. If no, nothing is blocked; the direction round derives a brand with the owner. - Voice: product language (NL/EN/...), register (je/u/you), and whether this audience changes the standing voice default in VOICE.md.
Feel, accent, temperature and visual references are not asked here. They are the substance of the direction round in step 3, where the owner sees them rendered instead of described.
2. Choose the UI foundation: one source of truth for all UI
Before anything is made, exactly one foundation is fixed for this project's UI: a component library themed with the owner's brand, or a bespoke system of the project's own tokens and components. Bespoke is right when the look is part of the product's value, the brand requirements are strong, or the owner wants zero UI dependencies.
Do the research and arrive with one recommendation in a short paragraph: what it is, why it
fits this product, what it costs, and the one real alternative beside it with what would have to
be true to prefer it (bespoke is the named alternative to every library, and vice versa). Verify
the candidate's maintenance, licence and accessibility from its official docs, live, never model
memory. docs/design/reference/ui-library-showcase.html holds one page per common React library
plus the bespoke option; say it exists and open it on request, never hand it over as homework.
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.
- 16d ago Changed · -87 lines · +106 tokens per session 749d909ce3bf
- 1mo ago Changed · +45 lines 5d1d0b596df8
- 1mo ago First seen · 152 lines · 0 tokens per session scan A e83274d540d5
design is a skill published in the GitHub repository Tradebaas/Groundwork (2 stars, last pushed 17d ago), licensed MIT. It adds 106 tokens to every session and 1,709 once invoked, about $0.0004 per session on Opus 5.5. 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
review-creative
Audit customer-facing work for UX, accessibility, brand fit, credibility, and generic AI output. Use for design, marketing, document, presentation, or visual review.
design-interaction
Design the interaction + feedback + error flows for a user-facing surface (CLI, API, or web). On-demand — run when the ux-engineer is consulted on an interaction contract.
design-experience
Build distinctive production-grade app and web interfaces. Use for UI/UX, responsive states, accessibility, visual systems, redesigns, or frontend polish.
design-token-component-contract
Repo-scoped workflow for mapping visual product specs into token and component contracts. Use only when this repository opts into docs-to-production harness execution.
visual-target-ingest
Repo-scoped workflow for turning generated PNG/SVG visual targets into reviewable screen contracts. Use only when this repository opts into docs-to-production harness execution.
product-usability
Repo-scoped workflow for product usability checks in docs-to-production implementation. Use only when this repository opts into docs-to-production harness execution.