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 mgh3326/auto_trader --skill design-systemgit clone --depth 1 https://github.com/mgh3326/auto_traderWrote 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/mgh3326/auto_trader/design-system)<a href="https://agentmods.dev/skills/mgh3326/auto_trader/design-system"><img src="https://agentmods.dev/badge/skills/mgh3326/auto_trader/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/mgh3326/auto_trader/design-system"><img src="https://agentmods.dev/badge/skills/mgh3326/auto_trader/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 | $0.00080 | $0.00416 |
| Opus 5.5 | $0.00032 | $0.00166 |
| Sonnet 5.5 | $0.00016 | $0.00083 |
| Haiku 4.5 | $0.00008 | $0.00042 |
Grade A, and why
auto-trader-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 26d 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
Read the README.md file within this skill, and explore preview/*.html. The shared tokens stylesheet lives at app/static/css/colors_and_type.css (served as /static/css/colors_and_type.css).
- For visual artifacts (slides, mocks, throwaway prototypes): copy
colors_and_type.cssinto the artifact and build static HTML that follows the patterns documented in the README — shell + dark header band + warm-neutral panels. - For production code changes in the
mgh3326/auto_traderrepo: apply the README's Migration plan section page-by-page. Prefer replacing per-page:rootblocks with a shared import ofcolors_and_type.css.
Key touchstones:
- Target-direction template:
app/templates/screener_dashboard.html. - Legacy pages to migrate:
login.html,register.html,admin_users.html,nav.html,base.html,error.html. - KR gain/loss convention: 상승 = red (
#9A1C1C), 하락 = blue (#0F4C9C). - Icons: Bootstrap Icons 1.11.3 via CDN. No emoji.
- Copy is operator-first, bilingual (Korean for chrome, English for technical/API terms).
If the user invokes this skill without guidance, ask what they want to build (new dashboard? migrate a legacy page? an isolated component?), ask a few follow-up questions about market + surface + density needs, and act as an expert designer who outputs HTML artifacts or production CSS, depending on the need.
What ships with it
15 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.
- preview/01-surfaces.html 1.6 KB
- preview/02-semantic-colors.html 2.1 KB
- preview/03-type.html 2.2 KB
- preview/03b-type-weights.html 2.0 KB
- preview/04-spacing-radius.html 1.8 KB
- preview/05-elevation.html 1.5 KB
- preview/06-buttons.html 1.9 KB
- preview/07-badges.html 1.9 KB
- preview/08-inputs.html 1.6 KB
- preview/09-shell-kpi.html 1.4 KB
- preview/10-table.html 2.0 KB
- preview/11-states.html 1.5 KB
- preview/12-iconography.html 1.4 KB
- preview/13-migration.html 1.9 KB
- README.md 22 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.
- 26d ago Changed c8f6d2e7a035
- 1mo ago First seen · 20 lines · 80 tokens per session scan A eeb171faac1f
auto-trader-design is a skill published in the GitHub repository mgh3326/auto_trader (10 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 416 once invoked, about $0.0003 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
visual-code-gen
Lane policy, quality rubric, and runtime contract for Code Studio outputs. USE THIS SKILL whenever the user asks for a simulation, interactive widget, mini app, dashboard, quiz, search-result explorer, or any bespoke interactive surface that ships rendered code (HTML + CSS + JS, SVG, or Canvas). TRIGGER for queries…
wiii-pointy
Wiii có một body — cursor 🟠 ở góc dưới phải màn hình LÀ cánh tay/ngón tay của Wiii. Khi Wiii nghĩ về một UI element trên màn hình, body tự nhiên trỏ đến đó. Đây KHÔNG phải tool — đây là embodied identity. TRIGGER khi user hỏi 'ở đâu', 'chỗ nào', 'chỉ cho tôi', 'click vào đâu', 'where is', 'show me how', 'point to'…
ui-design
Design-quality reference for financial-research visual output: typography, color, composition, and avoiding generic AI aesthetics.
billing-stripe
Work with Stripe billing — subscriptions, plans/prices, the Customer Portal, credits, usage metering, invoices, and webhook events. Use when changing plans, handling a new Stripe webhook, debugging a payment/subscription flow, or touching credit balances and usage.
financial_risk_modeling
A set of rules for building financial risk models for fraud detection, credit assessment, and suspicious-transaction monitoring. It covers data preparation, model choices, evaluation, and audit-ready outputs.
financial_timeseries
A set of rules for building financial time-series forecasting models for values such as exchange rates, prices, trading volume, and credit limits. Time-series data is ordered by time, so future information must not enter the past during training.