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 kavo-labs/kavo --skill policygit clone --depth 1 https://github.com/kavo-labs/kavoWrote 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/kavo-labs/kavo/policy)<a href="https://agentmods.dev/skills/kavo-labs/kavo/policy"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/policy/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/kavo-labs/kavo/policy"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/policy.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 | $0.00077 | $0.01563 |
| Opus 5 | $0.00039 | $0.00781 |
| Sonnet 5 | $0.00015 | $0.00313 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
policy 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 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.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Policy authorization reference
policy refuses a request before its handler runs. Each standard operation
on an entity can carry a rule evaluated against context.principal and,
when the rule needs it, the loaded row — a rule that fails answers 403
with KAVO_FORBIDDEN. Full detail: docs/features/policy.md and
ADR-0032/ADR-0033.
Wiring context.principal itself is the global-config/kavo-decorator
skills' territory (an app's own auth layer) — policy only ever reads it.
Config shape
import { and, authenticated, filtered, or, owner, permission, role } from "@kavo/core";
@Kavo(Post, {
operations: {
createOne: { policy: authenticated() },
findMany: { policy: permission("post:read") },
findOne: { policy: or(role("admin"), owner("authorId")) },
updateOne: { policy: and(permission("post:update"), owner("authorId")) },
},
})
policy is set per operation, at operations.<id>.policy — there is no
entity-scope policy map (ADR-0033; a leftover root-level policy map
fails at bootstrap, naming this path as the replacement). An operation with
no policy entry is unrestricted — opt-in per operation, not a global
switch. policy takes a PolicyNode only — build multi-permission checks
with and(permission("a"), permission("b")) (ADR-0032, amended by #242: the
array shorthand was removed since the DSL already covers everything it
could express).
Node types
| Node | Passes when |
|---|---|
permission(name) |
principal.permissions contains name |
role(name) |
principal.roles contains name |
authenticated() |
principal.userId is set |
owner(field = "userId") |
the row's field equals principal.userId; owner("author.id") walks a nested value |
filtered(field) |
context.query.filter carries a condition on field, anywhere in the AST |
when(({ context, entity, resource, operation, params }) => ...) |
the predicate returns true — escape hatch for anything else |
and(...) / or(...) / not(...) |
short-circuit composition; not negates its single child |
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 Changed · -48 lines · -17 tokens per session 5fe0bf73d11f
- 7d ago First seen · 167 lines · 94 tokens per session scan A 13c70eb7a47c
policy is a skill published in the GitHub repository kavo-labs/kavo (14 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,563 once invoked, about $0.0004 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 2026-09-02.
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.
procedure
Vovk.ts procedures — 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 handler, server action, form submission, controller, validation with Zod / Valibot /…
rpc
Vovk.ts RPC client — how vovk generate turns controllers into type-safe client modules, composed vovk-client 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), createTool() (standalone tools, no controller/procedure needed), @operation.tool({ name, title, description, hidden }) decorator, x-tool metadata, ToModelOutput.DEFAULT vs ToModelOutput.MCP formatters, the tools + toolsByName return shape, the meta…
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, the decorate() alternative for…
mixins
Vovk.ts OpenAPI mixins — importing third-party OpenAPI 3.x schemas as typed client modules that share the same call signature as native Vovk RPC modules. Use whenever the user asks to "call a third-party API from my Vovk app", "mixin an OpenAPI schema", "import an OpenAPI spec as a client", "wrap an external service…