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 finom/vovk --skill proceduregit clone --depth 1 https://github.com/finom/vovkWrote 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/finom/vovk/procedure)<a href="https://agentmods.dev/skills/finom/vovk/procedure"><img src="https://agentmods.dev/badge/skills/finom/vovk/procedure/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/finom/vovk/procedure"><img src="https://agentmods.dev/badge/skills/finom/vovk/procedure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 201 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 100 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00354 | $0.06172 |
| Opus 5.5 | $0.00142 | $0.02469 |
| Sonnet 5.5 | $0.00071 | $0.01234 |
| Haiku 4.5 | $0.00035 | $0.00617 |
Grade A, and why
procedure 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 yesterday.
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.
These URLs = plain HTTP — `curl`, `httpx`, `fetch`, any client works. Typed RPC clients (generated `@/client`, `vovk-python`, `vovk-rust`) wrap same endpoints with validation + inferred types; conveniences, not only acce How it starts
The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vovk.ts procedures
Procedure = typed, validated server-logic unit. Built with procedure({ ... }).handle(...). Atom of every Vovk app.
Mental model:
- Procedure valuable alone. Typed server function — call via
.fn()from RSC, server actions, SSR/SSG/PPR, any server code. No HTTP. - HTTP decorator (
@get,@post,@put,@patch,@del) OPTIONAL. Add only when exposing procedure as HTTP endpoint (also makes callable via generated RPC client from browser).
Opposite of most frameworks: procedures first, HTTP opt-in.
Procedure, minimally
import { procedure } from 'vovk';
import { z } from 'zod';
class UserController {
static getUser = procedure({
params: z.object({ id: z.string().uuid() }),
output: z.object({ id: z.string(), email: z.email() }),
}).handle(async (_req, { id }) => {
return UserService.byId(id); // plain call
});
}
What you have:
- Typed, validated procedure.
- Callable from ANY server code via
UserController.getUser.fn({ params: { id: '…' } }). - Not HTTP endpoint. Not in generated RPC client.
Expose over HTTP — add HTTP decorator:
import { z } from 'zod';
import { get, prefix, procedure } from 'vovk';
import UserService from './user-service';
@prefix('users')
export default class UserController {
@get('{id}')
static getUser = procedure({
params: z.object({ id: z.string().uuid() }),
output: z.object({ id: z.string(), email: z.email() }),
}).handle(async (_req, { id }) => {
return UserService.byId(id);
});
}
Now also GET /api/users/{id} and available as UserRPC.getUser(...) on client.
Deciding: decorator or no?
When user says...
| User intent | What to build |
|---|---|
| "Build users page" / "load X on server" / "dashboard showing Y" | Procedure, no decorator. Call via .fn() from server component. |
| "Server action for form submit" | Procedure, no decorator. Call via .fn() inside 'use server' function. |
"Add /api/users endpoint" / "expose X as API" / "browser needs to call it" |
Procedure + HTTP decorator. |
| "Users page AND also API" | Procedure + HTTP decorator. Call .fn() from server component; RPC client covers browser path. |
| "Internal helper used only from other procedures" | Plain service function, not procedure. Use procedure only when you want validation/types as contract. |
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.
- yesterday Changed 875008366caa
- 5d ago Changed · -24 lines · +18 tokens per session 10c01d95ce9a
- 10d ago Changed 444a4adfb136
- 11d ago Changed · +2 lines 0cae2729b9e0
- 12d ago Changed · -25 lines 9a848af6b7e0
- 17d ago Changed · -6 tokens per session a38a2da3b4a3
- 1mo ago First seen · 527 lines · 342 tokens per session scan A 1de2ffaf0e17
procedure is a skill published in the GitHub repository finom/vovk (53 stars, last pushed 2d ago), licensed MIT. It adds 354 tokens to every session and 6,172 once invoked, about $0.0014 per session on Opus 5.5. 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
ocli-api
Turn any OpenAPI, Swagger, or OpenRPC API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.
webmcp
Build agent-friendly web apps with the W3C Web Model Context API (WebMCP). Use when exposing frontend features as structured tools for in-browser AI agents, adding document.modelContext tools to React/Next.js apps, designing tool schemas for dashboards or admin UIs, or making existing UI automatable without DOM…
composition-patterns
Design reusable React component APIs that scale — compound components, lifted state, generic context, explicit variants. Use when a component is growing boolean props (isThread, isEditing…), when building a component library, or when reviewing component architecture. Includes React 19 API changes.
domain-driven-design
Model software around the business domain — bounded contexts, aggregates, entities vs value objects, domain events, and ubiquitous language. Use when writing an SRS/SDD, deciding how to split features into RonyKit service modules, designing internal/domain types, placing invariants, integrating with another service or…
add-resource
Add a complete REST resource (controller, validation, errors, and tests) to a Chassis project the idiomatic way. Use when the user asks to add an endpoint, resource, CRUD, model, or route to a Chassis / decorator-driven Express + TypeScript backend.
expressjs-development
Comprehensive Express.js development skill covering routing, middleware, request/response handling, error handling, and building production-ready REST APIs.