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 clubpay/ronykit --skill webmcpgit clone --depth 1 https://github.com/clubpay/ronykitWrote 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/clubpay/ronykit/webmcp)<a href="https://agentmods.dev/skills/clubpay/ronykit/webmcp"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/webmcp/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/clubpay/ronykit/webmcp"><img src="https://agentmods.dev/badge/skills/clubpay/ronykit/webmcp.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 | $0.00069 | $0.02370 |
| Opus 5.5 | $0.00028 | $0.00948 |
| Sonnet 5.5 | $0.00014 | $0.00474 |
| Haiku 4.5 | $0.00007 | $0.00237 |
Grade A, and why
webmcp 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WebMCP (agent-friendly frontend)
Expose your app's real business logic as structured tools agents can discover and call — instead of clicking buttons or scraping the DOM.
Every agent-ready page ships two interfaces:
- Human UI — the existing components, forms, and navigation.
- Agent tool surface — named tools with JSON Schemas that call the same handlers, stores, and API clients the UI uses.
Keep one source of truth. If a human click and an agent tool call would diverge, fix the architecture before adding more tools.
When to use
- Adding WebMCP /
document.modelContextsupport to a React or Next.js app. - Designing tool names, schemas, and descriptions for dashboards, admin consoles, or operational UIs.
- Making filters, search, CRUD, navigation, or checkout flows agent-callable.
- Reviewing whether a frontend is safe and reliable for AI agents.
Combine with nextjs-modern (App Router boundaries), dashboard-ui (tool
granularity for admin screens), ux-quality (human + agent UI stay in sync),
and frontend-testing (verify tools, not just components).
WebMCP vs related protocols
| Surface | What it is | When to use |
|---|---|---|
WebMCP (document.modelContext) |
W3C draft: page registers client-side tools for in-browser agents | Your website exposes what it can do while the user has the tab open |
| MCP (Model Context Protocol) | Server protocol: tools on a backend or desktop process | Backend services, DBs, CLIs — not a substitute for live page state |
| mcp-dashboards | MCP server that renders charts inside AI chat clients | Visualize data in the conversation — complementary, not WebMCP |
| DOM automation (Playwright, etc.) | Agent guesses selectors | Last resort when no tools exist; brittle and slow |
WebMCP is not a replacement for your REST/OpenAPI backend. Agents still need auth, rate limits, and server validation. Tools are a typed façade over logic you already run in the browser.
What ships with it
4 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.
- 1mo ago First seen · 217 lines · 69 tokens per session scan A dad747b5f752
webmcp is a skill published in the GitHub repository clubpay/ronykit (38 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 69 tokens to every session and 2,370 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
procedure
Vovk.ts procedures in depth (base already has a complete endpoint, validation, errors and status codes) — atomic unit of server-side logic in Vovk project. Use whenever user asks to build ANYTHING producing or consuming data on server — page loading data ("users page", "dashboard", "product list"), endpoint, API…
rpc
Vovk.ts RPC client — how vovk generate turns controllers into type-safe client modules, composed vs segmented clients, call shape (apiRoot, params, body, query, meta, init, disableClientValidation, validateOnClient, interpretAs, transform, fetcher), customizing generation via outputConfig.imports.fetcher +…
tools
Building LLM tools with Vovk.ts — deriveTools() (procedures → tools) returning a StandardToolV0[] array, standalone tools via the standard-tool package, @operation.tool({ name, title, description, hidden, meta }) decorator, x-tool metadata, ToModelOutput formatters (DEFAULT, MCP, RAW), the merged inputSchema, the meta…
base
Vovk.ts essentials — ALWAYS load first for any Vovk.ts task, including building a back end or API in a project that has vovk.config. or .vovk-schema/. Holds what a typical build needs, checked against vovk 4's code - project layout, a complete endpoint, how requests, validation and errors behave, status codes, a…
decorators
Vovk.ts decorators — built-in (@prefix, @operation, @get/@post/@put/@patch/@del, .auto()) and custom via createDecorator. Covers authorization / auth decorators, middleware-style wrapping (pre-handler + post-handler logic), req.vovk.meta() for cross-decorator state, stacking order, and the local (.fn()) vs HTTP…
jsonlines
Vovk.ts JSON Lines streaming — generator handlers (function, async function), the iteration validation option, validateEachIteration, the JSONLinesResponder manual API, progressive responses via progressive(), consuming streams from the RPC client (async iteration, using, asPromise, onIterate, abortController), and…