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 agentmods add skills/finom/vovk/bundlenpx skills add finom/vovk --skill bundlegit clone --depth 1 https://github.com/finom/vovkWhat 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 | $0.00250 | $0.03587 |
| Opus 5 | $0.00125 | $0.01793 |
| Sonnet 5 | $0.00050 | $0.00717 |
| Haiku 4.5 | $0.00025 | $0.00359 |
Grade A, and why
bundle 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 2d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
Vovk is bundler-agnostic — `esbuild`, `tsup`, `tsdown`, even `child_process` shell-out work. Only **tsdown** tested by Vovk's authors; docs warn: **pin `[email protected]`** until newer versions confirmed compatible. How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vovk.ts vovk bundle
vovk bundle packages composed TypeScript client as zero-dep npm package — pre-built JS + .d.ts, auto-gen package.json, auto-gen README.md w/ samples, ready for npm publish. Release step: vovk generate → in-project client for dev; vovk bundle → distributable SDK installed from registry.
TypeScript-only. Despite name, ships no Python/Rust clients. Those have own templates (py / pySrc / rs / rsSrc) and own publish flows — see python and rust skills.
Scope
Covers:
- 4-step bundle workflow.
bundle.buildasync function (required) + canonical[email protected]recipe.bundle.outputConfigfields (origin,package,reExports,imports,requires,readme,samples,includeSegments/excludeSegments).- Default directory layout (
tmp_prebundle→dist). - Full CLI flag list including
--openapi-*mixin family. - What's bundled / omitted (no
openapi, noschemaentry point — butschemastill importable as named export). npm publish distflow + consumer-side usage.deriveToolsintegration (bundled modules feed it identically).
Out of scope:
- In-project
vovk-clientgeneration →rpcskill. - Python client publishing (PyPI) →
pythonskill. - Rust client publishing (crates.io) →
rustskill. - Mixin authoring (consumed here as bundle inputs) →
mixinsskill.
bundle vs generate
| Command | Purpose | Output | When |
|---|---|---|---|
vovk generate |
In-project TypeScript client + OpenAPI spec | node_modules/.vovk-client/, .vovk-schema/ |
Every build (prebuild hook), on schema changes during vovk dev. |
vovk bundle |
Publishable npm package — pre-built JS + .d.ts + package.json + README.md |
dist/ ready for npm publish |
Ship SDK outside Next.js app. |
Don't run vovk bundle in normal dev; in-project client faster. Bundle when you need registry artifact.
How bundling works
- Vovk gens TypeScript client into
prebundleOutDir(defaulttmp_prebundle) viatsBasetemplate — uncompiled.tssource. - Vovk calls your
bundle.build({ entry, outDir, prebundleDir })async fn. Plugs in any bundler (tsdown only tested one) to compileentry(thetmp_prebundle/index.ts) → JS +.d.tsunderoutDir(defaultdist). - Vovk emits
package.jsonandREADME.mdfrompackageJsonandreadmetemplates intooutDir. - Vovk deletes
prebundleOutDirunlesskeepPrebundleDir: true(handy for debugging prebundled source).
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.
- 2d ago First seen · 255 lines · 250 tokens per session scan A 571e4c77238c
bundle is a skill published in the GitHub repository finom/vovk (52 stars, last pushed 5d ago), licensed MIT. It adds 250 tokens to every session and 3,587 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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 API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.
react-performance
Optimize React/Next.js runtime performance — eliminate waterfalls, shrink bundles, cut unnecessary re-renders, and speed up rendering. Use when writing, reviewing, or refactoring components for speed, or chasing slow renders, large bundles, janky interactions, or high TTFB/LCP/INP.
ronykit-framework
Orchestrates RonyKit service development using the ronyup MCP server (knowledge resources, prompts, scaffold tools). Use when the user mentions RonyKit, ronyup, EdgeServer, contracts, scaffolding a workspace or feature, implementing API handlers and services, frontend bootstrap, integration tests, or design documents…
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.
storybook
Author and maintain Storybook stories with CSF 3.0 best practices — args, decorators, parameters, and config. Use when creating or editing .stories. files, configuring .storybook/, or ensuring every UI component ships with stories.
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…