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 mission69b/t2000 --skill t2000-design-systemgit clone --depth 1 https://github.com/mission69b/t2000Wrote 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/mission69b/t2000/t2000-design-system)<a href="https://agentmods.dev/skills/mission69b/t2000/t2000-design-system"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-design-system.svg" alt="Measured on agentmods" 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 | $0.00130 | $0.01276 |
| Opus 5 | $0.00065 | $0.00638 |
| Sonnet 5 | $0.00026 | $0.00255 |
| Haiku 4.5 | $0.00013 | $0.00128 |
Grade A, and why
t2000-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 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
t2000 Design System (copy-in tokens + per-app shadcn)
Updated 2026-07-01. The old model —
@t2000/uias a runtime dependency shipping tokens and shadcn primitives — was retired. It broke consuming apps: its "tokens" bundled a full marketing stylesheet (reset + element typography +!importantresponsive hacks), and packaged shadcn primitives can't be styled by a consumer's Tailwind (node_modules isn't scanned) → padding/hover/cards silently broke on platform.t2000.ai. shadcn is copy-in by design; so are our tokens now.
The model — two things, decoupled
-
VALUES are shared by COPY-IN, not by dependency. Each app that ships UI owns its own tokens file — pure CSS custom properties only (Geist
--ds-*palette, semantic--fg/--bg/--bg-elevated/--border, radii, spacing, fonts). No element selectors, resets, utilities,@media, or!important— so it's safe to drop into any app. There is no monorepo tokens directory to import from — after kill-web (2026-08-03) the t2000 monorepo is docs + packages only; the live copies are in the audric repo (console, Connect). New surface → copy from the console's tokens, then map the vars you use into Tailwind via@theme inline. -
COMPONENTS are shadcn primitives, owned per-app in
components/ui/. Use them where interaction / a11y justifies (buttons, inputs, dialogs, tables, dropdowns, tooltips, command palettes, sidebars). Never consume a component package. Bespoke marketing/utility layout (heroes, section grids, a feed) can stay raw JSX + tokens — don't shadcn-ify a landing page for its own sake.
House theme
- Dark is canonical. The family look is a seamless near-black:
--bg #08090a,--bg-elevated #0f1113(cards/popovers), hairlinergba(255,255,255,.08)borders. Intentionally darker than raw Geist surfaces (itsgray-100 #1a1a1a/.14read too "app-chrome"). - Apps read the semantic tokens (
--bg/--bg-elevated/--border), NOT the raw--ds-gray-*primitives (those are the palette source). - Per-app accent is the one knob:
:root { --t2k-accent: <brand> }— emerald blue (t2000.ai). shadcn apps map the house values into their own token slots (--background/--card/--border…) because shadcn's names collide with the canonical's--border/--font-*/--radius-*(importing the file would cycle) — so copy the values in.
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 · 86 lines · 130 tokens per session scan A b5749c7a3acb
t2000-design-system is a skill published in the GitHub repository mission69b/t2000 (23 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 1,276 once invoked, about $0.0006 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
agent-payment-stats
Cross-protocol agent-economy payment metrics from Barker's index. x402 (Base) volume is on-chain verifiable; ACP / AP2 / MPP / AP4M figures are self-reported claims. Separates real vs nominal volume by filtering wash/noise sellers. Use when users ask about x402 volume, agent payment stats, agent economy metrics, or…
swarmwage-hire
Discover, inspect, dry-run, hire, and pay AI capabilities through Swarmwage. Start with wallet-free capability search and x402 reliability checks; use a dedicated USDC wallet only for real hires or paid external x402 calls.
swarmwage-publish
Publish your agent's capabilities to the Swarmwage registry and earn USDC for each call. Lets your agent advertise services (image generation, audio transcription, charting, custom domain workflows…) on the open agent hire protocol — other AI agents discover you, hire you with one function call, and pay you in USDC on…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
presentation-design
Designs slide decks and one-pagers that carry an argument rather than decorate one — deck structure, headlines that state the takeaway, charts that make a single point, and the different rules board decks and conference talks follow. Use this to build or fix a pitch deck, board deck, or conference talk, to design a…
ux-product-auditor
Audits a website, app, onboarding flow, or design for usability, conversion, and product problems, tying every finding to a business outcome and a severity. Use this to review an interface, diagnose low conversion or activation, find where users drop off, get structured product feedback, or decide which UX fixes to…