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 composite-primary-keysgit 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/composite-primary-keys)<a href="https://agentmods.dev/skills/kavo-labs/kavo/composite-primary-keys"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/composite-primary-keys/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/composite-primary-keys"><img src="https://agentmods.dev/badge/skills/kavo-labs/kavo/composite-primary-keys.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 15 findings, up to medium
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 →
- medium Memory Poisoning · line 73 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 79 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 81 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 73 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 73 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 75 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 75 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 77 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 78 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 79 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 79 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 80 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 80 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 81 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 81 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 | $0.00099 | $0.01217 |
| Opus 5 | $0.00049 | $0.00609 |
| Sonnet 5 | $0.00020 | $0.00243 |
| Haiku 4.5 | $0.00010 | $0.00122 |
Grade A, and why
composite-primary-keys 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 8d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Composite primary key reference (@kavo/typeorm)
An entity with more than one @PrimaryColumn — a natural key with no
surrogate id — is supported, TypeORM only:
@Entity()
export class UserSentence {
@PrimaryColumn("uuid")
userId!: string;
@PrimaryColumn()
topic!: string;
@Column()
key!: string;
}
EntityMetadata.compositeIdFields reports the key columns, in declaration
order. idField still exists (the first declared column, for callers that
only ever need one name) but nothing that addresses a row's real identity
may rely on it alone once compositeIdFields is set.
Route id encoding
One path segment, key columns joined by ~:
GET /user-sentences/u1~billing → { userId: "u1", topic: "billing" }
A literal ~ inside a value is escaped by doubling it (~~) — the id has
already passed URL decoding by the time Kavo sees it, so percent-escaping
the separator would be silently invisible. encodeCompositeId/
decodeCompositeId (@kavo/core's barrel) implement the codec; a malformed
id (wrong part count) is a clean 400, never a driver error.
Writable defaults
Key columns are creatable but not updatable: createOne accepts them
(a natural key the client supplies), updateOne/patchOne silently drop
them from the body — the row's identity doesn't change after creation.
This is the one case where creatable's and updatable's shared default
diverges; narrow either explicitly (see the kavo-decorator skill) if that
default is wrong for an entity.
Pagination
Offset, page, cursor, and since all work. Cursor/since force the sort's
tail to the full compositeIdFields tuple, in declaration order, instead
of a single idField — sort=-createdAt,userId,topic, not
sort=-createdAt,userId. A since token's id half reuses the same
~-delimited encoding a route id uses.
Association by id (ADR-0014)
Works in both directions:
- As a relation's source — an owner entity can
include=it normally. - As a relation's target — a write body names it as an object keyed by
each column (
{ owner: { userId: "u1", topic: "billing" } }) or the bare~-delimited scalar ({ owner: "u1~billing" }). Either narrows to the target's real column names before it reaches the adapter.
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.
- 8d ago First seen · 85 lines · 99 tokens per session scan A 7a5f67742498
composite-primary-keys is a skill published in the GitHub repository kavo-labs/kavo (14 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,217 once invoked, about $0.0005 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
db-infra-mocks
Propose minimal seams and local substitutes so tests run without real RDBMS/Redis/Mongo infrastructure.
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…
draft-release-notes
Author the committed release-notes file for a Prisma 8 release (stable or 8.0.0-rc.N) by enumerating the merged PRs since the previous release v tag (stable or -rc.N), resolving opaque TML-NNNN: titles via Linear context (never copied verbatim), triaging public-worthiness, and writing categorized notes — breaking…
record-upgrade-instructions
Record upgrade instructions alongside a Prisma Next breaking-change PR, so downstream consumers (users of @internal/ and authors of Prisma Next extensions) can apply the matching code translation automatically via the published upgrade skills. Use when you have refactored framework code and the test suite went red in…
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
triage-contributor-pr
Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…