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 agentmods add skills/basementstudio/xmcp/widget-designnpx skills add basementstudio/xmcp --skill widget-designgit clone --depth 1 https://github.com/basementstudio/xmcpWrote 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/basementstudio/xmcp/widget-design)<a href="https://agentmods.dev/skills/basementstudio/xmcp/widget-design"><img src="https://agentmods.dev/badge/skills/basementstudio/xmcp/widget-design.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.01388 |
| Opus 5 | $0.00024 | $0.00694 |
| Sonnet 5 | $0.00010 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
widget-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 4d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Widget Design Best Practices
Decision Framework
Platform Selection
Choose based on target client:
- GPT Apps: Target is ChatGPT. Requires
_meta.openaiwithwidgetAccessible: true. - MCP Apps: Target is any ext-apps client. Minimal config, works automatically.
Handler Type Selection
| Scenario | Handler | Reason |
|---|---|---|
| User interaction needed (buttons, inputs) | React (.tsx) |
State management with hooks |
| Display external widget library | Template literal | Just load scripts/styles |
| Dynamic content from tool params | React | Props flow naturally |
| Static HTML with no state | Template literal | Simpler, less overhead |
Rule of thumb: If unsure, start with React. Converting later is harder than starting simple.
Widget Design Principles
1. Widgets Are Not Web Apps
Widgets render inline in conversations. Design constraints:
- No navigation: Single-screen experience only
- Limited width: ~600-700px max in most clients
- Sandboxed: External resources need CSP declarations
- Ephemeral: May be re-rendered, don't rely on persistence
2. Immediate Value
Show useful content without requiring user action:
// Bad: Requires click to see anything
export default function Widget() {
const [data, setData] = useState(null);
return <button onClick={fetchData}>Load Data</button>;
}
// Good: Shows data immediately
export default function Widget({ query }) {
const [data, setData] = useState(null);
useEffect(() => { fetchData(query).then(setData); }, [query]);
return data ? <Results data={data} /> : <Loading />;
}
3. Visual Hierarchy in Limited Space
With limited width, hierarchy matters more:
<div className="space-y-4">
{/* Label: small, muted, uppercase */}
<div className="text-sm text-zinc-500 uppercase tracking-wider">Temperature</div>
{/* Value: large, prominent */}
<div className="text-5xl font-light">72°F</div>
{/* Supporting: medium, secondary */}
<div className="text-zinc-400">Feels like 68°F</div>
</div>
What ships with it
1 file 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.
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.
- 4d ago First seen · 232 lines · 49 tokens per session scan A ba492f496c14
widget-design is a skill published in the GitHub repository basementstudio/xmcp (1,325 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,388 once invoked, about $0.0002 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
gh-pr-description
Drafts and reviews GitHub pull request descriptions for the eve repository. Use when opening, updating, or reviewing a PR, or when summarizing a branch for reviewers.
technical-writing
Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current…
om-auto-update-changelog
Open Mercato releases must keep CHANGELOG.md, UPGRADENOTES.md, and version-specific downstream migration skills aligned. Apply this contract after the external skill resolves {version}, {date}, and the previous changelog release, but before it edits files or delegates to om-auto-create-pr.
om-ds-guardian
Design System Guardian for Open Mercato. Use for frontend UI work, design-system compliance reviews, semantic token migration, hardcoded color or typography cleanup, DS-compliant page scaffolding, and common DS violations such as arbitrary text sizes, raw color classes, or missing shared states. Prefer this skill…
om-integration-builder
Build integration provider packages for the Open Mercato Integration Marketplace (payment, shipping, data-sync, webhook). Scaffolds the npm package, adapter, credentials, widget injection, webhook processing, health checks, i18n, tests. Triggers on "build integration", "add provider", "integrate with…
om-integration-tests
Run and create QA integration tests (Playwright TypeScript), including executing the full suite, converting optional markdown scenarios, and generating new tests from specs or feature descriptions. Defers all environment boot/reuse to the om-prepare-test-env skill and attaches to the shared descriptor it writes. Use…