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 secondsky/sap-skills --skill sap-sac-custom-widgetgit clone --depth 1 https://github.com/secondsky/sap-skillsWrote 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/secondsky/sap-skills/sap-sac-custom-widget)<a href="https://agentmods.dev/skills/secondsky/sap-skills/sap-sac-custom-widget"><img src="https://agentmods.dev/badge/skills/secondsky/sap-skills/sap-sac-custom-widget/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/secondsky/sap-skills/sap-sac-custom-widget"><img src="https://agentmods.dev/badge/skills/secondsky/sap-skills/sap-sac-custom-widget.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00103 | $0.07335 |
| Opus 5 | $0.00051 | $0.03667 |
| Sonnet 5 | $0.00021 | $0.01467 |
| Haiku 4.5 | $0.00010 | $0.00734 |
Grade A, and why
sap-sac-custom-widget 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 7d 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.
The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
35 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.
- agents/openai.yaml 251 B
- README.md 8.8 KB
- references/advanced-topics.md 17 KB
- references/ai-assisted-composite-generation.md 16 KB
- references/best-practices-guide.md 14 KB
- references/browser-design-runtime.md 9.5 KB
- references/css-and-styling-compliance.md 7.4 KB
- references/echarts-integration.md 23 KB
- references/integration-and-migration.md 11 KB
- references/json-schema-reference.md 17 KB
- references/local-builder-workflow.md 6.3 KB
- references/production-widget-lessons.md 12 KB
- references/property-lifecycle.md 7.9 KB
- references/sac-import-packaging-lessons.md 13 KB
- references/sap-sample-widget-lessons.md 7.8 KB
- references/script-api-reference.md 18 KB
- references/verification-and-artifacts.md 6.2 KB
- references/widget-addon-guide.md 11 KB
- references/widget-discovery-intake.md 5.7 KB
- references/widget-templates.md 35 KB
- templates/basic-widget.js 6.3 KB runs code
- templates/builder-panel.js 6.2 KB runs code
- templates/data-bound-chart.js 8.8 KB runs code
- templates/design-runtime/design-runtime.json 3.7 KB
- templates/design-runtime/index.html 8.2 KB
- templates/design-runtime/runtime.css 4.6 KB
- templates/design-runtime/runtime.js 35 KB runs code
- templates/local-builder/builder-config.json 9.9 KB
- templates/local-builder/builder.css 4.8 KB
- templates/local-builder/builder.js 40 KB runs code
- templates/local-builder/index.html 15 KB
- templates/local-builder/server.mjs 1.8 KB runs code
- templates/styling-panel.js 12 KB runs code
- templates/widget.json-complete 4.5 KB
- templates/widget.json-minimal 614 B
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.
- 7d ago First seen · 584 lines · 103 tokens per session scan A c515ece19c62
sap-sac-custom-widget is a skill published in the GitHub repository secondsky/sap-skills (439 stars, last pushed 7d ago), licensed GPL-3.0. It adds 103 tokens to every session and 7,335 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
ds-frontend
Frontend design quality — design-system audit, token enforcement, component states, accessibility, responsive layout, theming. Use when building or reviewing UI for design consistency, a11y, or responsiveness.
framework-upgrade-guide
Analyze a TypeScript/Node project (Angular, React, or Vue), read its dependencies, flag deprecated/EOL packages and known vulnerabilities, and produce a careful stepwise major-by-major upgrade guide (e.g. Angular 15→16→17→18→19) written to a file. Use this whenever the user wants to upgrade, migrate, or modernize a…
fullstack-coder
Full-stack implementation agent that writes complete, production-ready code following an approved architecture and schema. Triggers on: write the code, implement features, build the app, code the MVP, generate codebase.
frontend-design
Use this skill when building UI components, designing frontend architecture, implementing styling systems, optimizing performance, ensuring accessibility, or creating production-grade interfaces. Trigger on keywords: frontend, component, UI, styling, React, Next.js, Angular, Tailwind, CSS, responsive, accessibility…
web-artifacts-builder
Use this skill when building multi-component web applications, interactive dashboards, complex React apps with state management, or any web artifact that requires routing, multiple views, or sophisticated UI interactions. Trigger on keywords: build a web app, dashboard, multi-page, React app, interactive tool, web…
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.