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 DemonDamon/AgenticX --skill b2b-desktop-design-systemgit clone --depth 1 https://github.com/DemonDamon/AgenticXWrote 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/demondamon/agenticx/b2b-desktop-design-system)<a href="https://agentmods.dev/skills/demondamon/agenticx/b2b-desktop-design-system"><img src="https://agentmods.dev/badge/skills/demondamon/agenticx/b2b-desktop-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/skills/demondamon/agenticx/b2b-desktop-design-system"><img src="https://agentmods.dev/badge/skills/demondamon/agenticx/b2b-desktop-design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00374 |
| Opus 5.5 | $0.00012 | $0.00150 |
| Sonnet 5.5 | $0.00006 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
b2b-desktop-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 2mo 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.
What it actually says
B2B Desktop Design System
Goals
Produce leading but pragmatic enterprise desktop visuals without copyrighted asset packs.
Checklist
Color & type
- Primary: indigo/violet OKLCH (
--primaryfamily) - Neutral surfaces:
--background,--surface-card,--text-strong - Type scale: 12 / 14 / 16 / 20 / 24 — max 3 weights on one screen
Layout & hierarchy
- AppShell: brand row + grouped sidebar + content canvas
- One primary action per view; secondary actions in overflow/menu
- Status/progress in dedicated panel — not mixed into nav labels
Components (POC minimum)
- Sidebar nav with active left accent bar
- PageHeader + Breadcrumb
- DataTable or card grid for list views
- Dialog/Sheet for destructive confirm
References (patterns only, do not paste assets)
- IBM Carbon spacing rhythm
- Arco Design layout density
- Ant Design Pro information architecture
Deliverables
Under output/<task_id>/design/:
design-system.md— tokens, spacing, component states- Wireframe: Figma link or
dashboard-wireframe.svgfallback
Figma MCP
When figma-mcp connected and FIGMA_API_KEY set, create/update a Figma file and record URL in design-system.md.
Accessibility
- WCAG AA contrast for primary text on surfaces
- Focus ring visible in light and dark themes
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.
- 2mo ago First seen · 57 lines · 31 tokens per session scan A 3ea93634a406
b2b-desktop-design-system is a skill published in the GitHub repository DemonDamon/AgenticX (988 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 374 once invoked, about $0.0001 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 2026-08-30.
b2b-desktop-design-system compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| b2b-desktop-design-systemDemonDamon/AgenticX | Skill | 988 | yesterday | Apache-2.0 | A | 31 | Claude Code, Codex |
| ads-dnacitedy/adclaw | Skill | 49 | 3mo ago | Apache-2.0 | A | 90 | Claude Code, Codex |
| brandkitSabilMurti/Seiza | Skill | 1 | 3mo ago | none | A | 11 | Claude Code, Codex |
| canvaasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 62 | Claude Code, Codex |
| hi-fi-designasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 27 | Claude Code |
| optionsasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 13 | Claude Code |
| wireframeasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 12 | Claude Code |