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 pnp/sharepoint-skills --skill sharepoint-safe-htmlgit clone --depth 1 https://github.com/pnp/sharepoint-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/pnp/sharepoint-skills/sharepoint-safe-html)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/sharepoint-safe-html"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/sharepoint-safe-html/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/pnp/sharepoint-skills/sharepoint-safe-html"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/sharepoint-safe-html.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 | $0.00120 | $0.05590 |
| Opus 5 | $0.00060 | $0.02795 |
| Sonnet 5 | $0.00024 | $0.01118 |
| Haiku 4.5 | $0.00012 | $0.00559 |
Grade A, and why
sharepoint-safe-html 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 9d 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 — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SharePoint Safe HTML
Generate a single self-contained .html file that works reliably when hosted in SharePoint or OneDrive and opened through preview, File Viewer, Teams, or an embedded iframe.
If a narrower installed skill matches the artifact type (for example, an executive report, dossier, scorecard, or roadmap), use that skill for content structure and apply this skill's safety and accessibility contract to the final HTML.
Core Contract
Create exactly one .html file that works with:
- No network access.
- No external files by default, except explicitly approved SharePoint/OneDrive live-linked
.csvor.xlsxdata files. - No external CSS, JavaScript, images, fonts, APIs, analytics, or CDNs.
- No privileged browser APIs.
- No secrets or tokens.
- No dependency on local filesystem paths.
- Semantic, accessible HTML that targets WCAG 2.2 AA unless the user explicitly asks for a different standard.
Assume SharePoint and OneDrive render the file inside a restricted sandboxed iframe. If it works locally but relies on anything outside the file, it is not SharePoint-safe.
SharePoint/OneDrive can live link up to 10 .csv or .xlsx files in the same folder as the HTML file, so the artifact updates when those files change. Treat this as the only approved external-file exception, and use it only when the user wants an auto-updating data-backed artifact.
Default Decision Rule
Prefer static, self-contained, CSS-driven HTML.
Use JavaScript only when the user explicitly needs interactivity and accepts that SharePoint/OneDrive sandbox behavior may vary. If JavaScript is used, it must be inline, dependency-free, non-networked, and progressive enhancement only. The artifact must remain useful if scripts are blocked.
Accessibility is not a final polish step. It must shape the content model, visual design, render logic, and validation pass.
Workflow
Step 1: Confirm the artifact purpose
Identify the requested output type and audience:
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.
- 9d ago First seen · 478 lines · 120 tokens per session scan A 5b29698fdffd
sharepoint-safe-html is a skill published in the GitHub repository pnp/sharepoint-skills (110 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 5,590 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
d3-viz
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke…
gsap-plugins
Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG…
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
threejs-interaction
Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.
gsap-core
Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion…
gsap-utils
Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the user asks about gsap.utils, clamp, mapRange, random, snap, toArray, wrap, or helper utilities in GSAP.