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 OpenLinkSoftware/ai-agent-skills --skill osdi-inclusion-enginegit clone --depth 1 https://github.com/OpenLinkSoftware/ai-agent-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/openlinksoftware/ai-agent-skills/osdi-inclusion-engine)<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/osdi-inclusion-engine"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/osdi-inclusion-engine/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/openlinksoftware/ai-agent-skills/osdi-inclusion-engine"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/osdi-inclusion-engine.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 | $0.00157 | $0.03195 |
| Opus 5 | $0.00078 | $0.01597 |
| Sonnet 5 | $0.00031 | $0.00639 |
| Haiku 4.5 | $0.00016 | $0.00319 |
Grade A, and why
osdi-inclusion-engine scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
8. **Deploy content**: WebDAV PUT each page's stripped content fragment as `content/{name}.html` under the site's `webdav_base`. Use curl per the standing curl-first rule; MCP tools only when no CLI path exists. How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSDI Inclusion Engine
Use this skill to inspect, configure, and deploy content into websites run by the OpenLink Inclusion Engine (OSDI): a Virtuoso-hosted system where a single index.vsp per site resolves /{page} requests to content/{page}.html in WebDAV, passes the document through HTML Tidy (unless its DOCTYPE is XHTML+RDFa), wraps it with a skin's XSLT (PostProcess.xslt), merges RDF data-islands, caches the rendered result in incleng..cache, and serves it.
All configuration lives in the RDF quadstore graph <urn:com.openlinksw.virtuoso.incleng>, accessed via the incleng..config_* SQL API — never the legacy incleng..sites table. Read references/config-api.md before issuing any config SQL.
Blocking Gate — This Is a Skin-Authoring Decision, Not a Deploy-Path Choice
Every chrome-bearing skin — legacy openlink/responsive in the inclusion-engine VAD, and modern matrix/bootstrap-2022 in the opl-skins VAD — unconditionally injects the corporate masthead and footer around whatever is in the source document's <body>. A page carrying its own <nav>/<header>/<footer> deployed under one of these skins stacks two sets of chrome.
The passthrough override (per-URL xslt_sheet → /DAV/VAD/inclusion-engine/skin/passthrough/xslt/PostProcess.xslt) avoids the stack, but its cost is too great to be a default: it freezes one page as a permanent one-off outside the skin system, forfeiting engine-supplied feeds links, canonical, JSON-LD SearchAction, analytics, OPAL widget, and site-wide nav consistency — forever, since nothing about the override is a stepping stone to anything better. Only use it as an explicit, time-boxed stopgap the user has chosen with that cost stated.
The real question is never "strip this one page to fit the current skin" — it's "does this new appearance become the site's skin?" A homepage mockup only has opinions about the homepage; every site has a multiplicity of other page types (contact forms, customer-snapshot/testimonial layouts, pricing, docs, etc.) that the mockup says nothing about. Treat every self-styled replacement as a candidate new skin, and resolve these design questions before writing any XSLT or touching DAV content:
What ships with it
7 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.
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.
- 10d ago First seen · 84 lines · 157 tokens per session scan A 7b4df28708e9
osdi-inclusion-engine is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed yesterday), licensed MIT. It adds 157 tokens to every session and 3,195 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…