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 bearlike/Assistant --skill st-widget-buildergit clone --depth 1 https://github.com/bearlike/AssistantWrote 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/bearlike/assistant/st-widget-builder)<a href="https://agentmods.dev/skills/bearlike/assistant/st-widget-builder"><img src="https://agentmods.dev/badge/skills/bearlike/assistant/st-widget-builder/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/bearlike/assistant/st-widget-builder"><img src="https://agentmods.dev/badge/skills/bearlike/assistant/st-widget-builder.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 | $0.00065 | $0.00813 |
| Opus 5.5 | $0.00026 | $0.00325 |
| Sonnet 5.5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
st-widget-builder 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 1mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
st-widget-builder
st-widget-builder is a sub-agent — delegate to it via spawn_agent. Do not write widgets yourself.
For a static, no-code panel, read generative-ui; use this skill when the result needs code or interactivity.
How to invoke
spawn_agent(
agent_type="st-widget-builder",
task="<data hand-off + purpose — see rules below>",
acceptance_criteria="widget_ready event emitted with app.py and data.json"
)
What goes in the task
The sub-agent has a component catalog and designs the layout itself. Your task must contain only two things:
- Purpose — one sentence: what does the user want to see?
- Data — the file path + field names the widget needs.
# ✓ Correct — data + purpose only
task=(
"Show the current AAPL stock price and recent price trend. "
"Data: /tmp/mewbo/aapl_data.json — fields: quote.price, quote.change, "
"quote.pct_change, quote.open, quote.high, quote.low, quote.volume, "
"daily[].date, daily[].close (30 days, newest first)."
)
# ✗ Wrong — prescribing layout (forces sub-agent away from its catalog)
task=(
"Build a header card with the price in large text, then a row of 5 "
"metric cards, then a green line chart titled '30-Day Price History'. "
"Use a dark theme with Altair."
)
Do not describe layout, sections, component types, chart axes, colors, or themes. The sub-agent's catalog (StockTickerCard, GitHubRepoCard, SearchResultCard, PlantUMLCard, …) already handles these consistently. Prescribing layout bypasses the catalog and forces custom code that looks worse.
Data hand-off
Write structured data to a file before spawning — never paste raw JSON into the task string. Stage it under /tmp/mewbo/ (or the session cwd): the file tools can only read inside /tmp/mewbo/, the cwd, and configured project roots, so a bare /tmp/... path would be unreadable by the sub-agent.
gh search repos --json name,description,stargazerCount,language,url \
--limit 10 "topic:streamlit" > /tmp/mewbo/gh_results.json
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.
- 1mo ago First seen · 71 lines · 65 tokens per session scan A 67e88014c413
st-widget-builder is a skill published in the GitHub repository bearlike/Assistant (44 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 813 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 2026-08-30.
Other skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
pr-screenshot-comparison
Create clear, polished before-and-after screenshots from the actual running product for a GitHub pull request. Use when a UI change needs visual proof: capture matching product states, crop to the relevant UI, stitch and caption one comparison image, attach it natively to the PR, and keep the image out of the…
typography
Apply professional typography principles to create readable, hierarchical, and aesthetically refined interfaces. Use when setting type scales, choosing fonts, adjusting spacing, designing text-heavy layouts, implementing dark mode typography, or when asked about readability, font pairing, line height, measure…
clean-copy
Cut interface copy that should not exist. Captions that restate a label, hints that pre-empt a worry the user never had, warnings that are scar tissue from a fixed bug. Use when writing or reviewing any user-facing string (labels, hints, empty states, toasts, confirmations, button text), or when asked to clean up or…
design-ui-style-guide
Create a visual system for a new or redesigned user interface. Generate exactly three image concepts and stop for user approval. After approval, create an HTML and CSS style guide with a representative demo. Do not use when the user supplies an approved design, requests a small edit, or skips visual exploration.
skill-icon-workflow
Create, update, or validate Codex skill icons. Use this skill for the small SVG, the 100x100 PNG, and the icon fields in agents/openai.yaml. Do not use it for app icons, favicons, badges, unrelated artwork, or skill work that does not include an icon.