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 kavo-decoratorgit 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/kavo-decorator)<a href="https://agentmods.dev/skills/kavo-labs/kavo/kavo-decorator"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/kavo-decorator/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/kavo-decorator"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/kavo-decorator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 34 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.
- high Tool Misuse · line 36 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 Prompt Injection · line 125 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 129 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00078 | $0.02500 |
| Opus 5.5 | $0.00031 | $0.01000 |
| Sonnet 5.5 | $0.00016 | $0.00500 |
| Haiku 4.5 | $0.00008 | $0.00250 |
Grade A, and why
kavo-decorator 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@Kavo() reference
@Kavo(Entity, config?) (packages/frameworks/nest/src/kavo.decorator.ts) is a
class decorator that builds the entity's operation registry at
class-decoration time and generates one Nest route per enabled entry:
@Kavo(UserEntity)
@Controller("users")
export class UserController {}
The bound DefaultKavoService<Entity> arrives later, via property injection
at onModuleInit (KavoBinder) — not through the constructor. Reach it
with boundKavoService(this), never constructor injection, inside a
@Kavo-decorated class.
Full detail: docs/internals/architecture/10-nestjs-integration.md.
Generated routes
| Operation | Route | Status |
|---|---|---|
createOne |
POST / |
201 |
findMany |
GET / |
200 |
findOne |
GET /:id |
200 |
updateOne |
PUT /:id |
200 |
patchOne |
PATCH /:id |
200 |
deleteOne |
DELETE /:id |
204 |
restoreOne |
PATCH /:id/restore |
200 |
purgeOne |
DELETE /:id/purge |
204 |
restoreOne/purgeOne are off by default and turned on by config
(delete: { strategy: "soft" } enables restore; operations: { purgeOne: true }
enables purge) — decoration time has no ORM metadata to auto-detect them from.
config — the second argument (EntityConfig<Entity>)
interface EntityConfig<Entity, CreateDto, UpdateDto, PatchDto, QueryDto, ItemDto, ListDto>
extends Omit<DeepPartial<KavoSettings>, "operations"> {
schema?: EntitySchema<...>; // { input: { create/update/patch/query }, output: { item/list } }; class or validator per slot
allowed?: QueryAllowed<Entity>; // filterable/sortable/selectable field allowlists
operations?: Partial<Record<StandardOperationId, OperationConfig<Entity> | boolean>>;
}
schema— configure any of the bare-verb slots (input.create/update/patch/query,output.item/list) with a DTO class or a validator. Omitted slots derive from the entity.allowed— see below.operations.<id>—falsedisables the operation (no route, no service method reachable);trueenables one that is off by default (purgeOne,restoreOne). The long form,{ enabled?, handler?, meta? }, additionally lets you swap theOperationHandleror supply routemeta(method,path,successStatus, orenabled: falseto keep it service-only).- Settings keys (
pagination,limits,search,errors,relations,delete,bulk) inherited fromDeepPartial<KavoSettings>override the global default for this entity only — see theglobal-configskill for the precedence chain these merge through, and the sections below for whatrelationsconfigures.
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 Changed · +1 lines 4fd30704b32c
- 2mo ago Changed 0e9e12f819b2
- 2mo ago Changed · +2 lines · -1 tokens per session 4ea198bffbbe
- 2mo ago First seen · 216 lines · 79 tokens per session scan A 74df3e8e2b6c
kavo-decorator is a skill published in the GitHub repository kavo-labs/kavo (17 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 2,500 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 2026-09-02.
kavo-decorator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kavo-decoratorkavo-labs/kavo | Skill | 17 | today | MIT | A | 78 | Claude Code |
| nestjs-expertpersonamanagmentlayer/pcl | Skill | 45 | 18d ago | Apache-2.0 | A | 81 | Claude Code |
| prisma-8prisma/orm | Skill | 48k | today | Apache-2.0 | A | 220 | Claude Code, Codex |
| nestjsericrisco/rsc-harness | Skill | 598 | today | MIT | A | 81 | Claude Code, Codex |
| webiny-api-cms-content-modelswebiny/webiny-js | Skill | 8.1k | today | none | A | 313 | Claude Code, Codex |
| webiny-api-architectwebiny/webiny-js | Skill | 8.1k | today | none | A | 93 | Claude Code, Codex |
| rpcfinom/vovk | Skill | 57 | today | MIT | A | 347 | Claude Code |