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 soft-deletegit 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/soft-delete)<a href="https://agentmods.dev/skills/kavo-labs/kavo/soft-delete"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/soft-delete.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 24 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 65 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 52 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 | $0.00072 | $0.01238 |
| Opus 5 | $0.00036 | $0.00619 |
| Sonnet 5 | $0.00014 | $0.00248 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
soft-delete 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 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.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Soft delete, restore & purge reference
Deleting a row can mean two things. Kavo resolves which one per entity, at
bootstrap, and every layer downstream reads that one answer instead of
re-deciding. Full detail: docs/internals/architecture/11-soft-delete.md.
Wire-level withDeleted=true grammar is in the query-grammar skill;
config precedence is in the global-config skill.
Opting in
@Entity()
class Owner implements SoftDeletable {
@DeleteDateColumn() deletedAt!: Date | null;
}
That's the whole opt-in for the common case — no @Kavo config needed.
DELETE /owners/:id now stamps the marker instead of removing the row, and
every read excludes stamped rows.
Strategy resolution (resolveSoftDelete)
| Settings | Result |
|---|---|
delete: false |
hard |
delete.strategy: "hard" |
hard |
delete.strategy: "soft" |
soft — no marker field on the entity is a config error |
delete.strategy: "auto" (default) |
soft when a marker field exists, else hard |
The marker field is the configured delete.field (default
"deletedAt") if the entity has that column, otherwise whatever the ORM
declares (@DeleteDateColumn in @kavo/typeorm). Explicit config wins over
detection; an entity with neither costs nothing.
This resolves at every settings scope, so one operation or a single call can narrow it:
@Kavo(Owner, {
operations: { deleteOne: { delete: { strategy: "hard" } } },
})
Operations
| Operation | Behavior |
|---|---|
deleteOne |
Hard or soft per the resolved strategy. Soft-deleting an already-deleted row → 409 KAVO_ALREADY_DELETED. |
restoreOne |
Clears the marker, returns the revived row in the item slot (no new DTO shape). A live row → 409 KAVO_NOT_DELETED. |
purgeOne |
Permanently removes an already-soft-deleted row. A live row → 409 KAVO_NOT_DELETED. Under hard it's just a delete. |
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 · -1 tokens per session dfdc86d36b4d
- 6d ago First seen · 111 lines · 73 tokens per session scan A ab345e2f6eb6
soft-delete is a skill published in the GitHub repository kavo-labs/kavo (12 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,238 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
servicenow-table-api
Foundational ServiceNow data access — generic Table API CRUD, Aggregate/stats roll-ups, and raw REST escape-hatch via the servicenow-api MCP server. Use when the agent must read, insert, update, patch, delete, count, or aggregate records in ANY ServiceNow table (including scoped app tables with no dedicated API), or…
prisma-8
Comprehensive guide for building with Prisma 8 (Prisma Next), the contract-first data layer. Use whenever working on Prisma code in a project that uses it — authoring or editing the data contract (contract.prisma, PSL, TypeScript builders), migrations, queries (db.orm / db.sql), runtime wiring (db.ts, middleware…
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
ocli-api
Turn any OpenAPI/Swagger API into CLI commands and call them. Search endpoints with BM25, check parameters, execute — no MCP server needed.
db-infra-mocks
Propose minimal seams and local substitutes so tests run without real RDBMS/Redis/Mongo infrastructure.
mail-time
Use when building, wiring, reviewing, or debugging MailTime and ostrio:mailer email queues for horizontally scaled Node.js, Bun, or Meteor apps. Trigger on MailTime, MongoQueue, RedisQueue, PostgresQueue, mailTimePreset, JoSk email scheduling, Redis Cluster / KeyDB Cluster / Valkey useHashTags, KeyDB…