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/latitude-dev/latitude-llm/testingnpx skills add latitude-dev/latitude-llm --skill testinggit clone --depth 1 https://github.com/latitude-dev/latitude-llmWhat 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 | $0.00041 | $0.01066 |
| Opus 5 | $0.00020 | $0.00533 |
| Sonnet 5 | $0.00008 | $0.00213 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
testing 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 3d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing conventions and in-memory databases
When to use: Writing or debugging tests, choosing unit vs integration style, Postgres/ClickHouse tests, regenerating ClickHouse test schema, or exporting test helpers from packages without pulling test code into production bundles.
Package exports (test code isolation)
Test utilities (fakes, in-memory DB helpers, fixtures) must not be exported from a package’s main entry (src/index.ts).
- Never re-export from
./test/or./testing/in the mainsrc/index.ts - To expose test helpers, add a
/testingsubpath inpackage.jsonexports:
{
"exports": {
".": "./src/index.ts",
"./testing": "./src/testing/my-test-helpers.ts"
}
}
- Consumers:
import { Fake } from "@platform/my-package/testing" - Biome
noRestrictedImportsblocks test paths in production source; tsdown fails the build if test code is resolved from prod entry points
Conventions
- Shared default environment: Node with globals enabled (
packages/vitest-config/index.ts) - Write tests, mostly e2e, some unit tests when logic is complex
- Unit tests: domain entities/use-cases/policies with fakes
- Contract tests: adapter compliance against domain ports
- Integration tests: infra-backed tests for Postgres/ClickHouse/Redis/BullMQ/object storage
- End-to-end tests: ingest boundary to query boundary across organization scoping
- Keep tests deterministic and isolated
- Prefer package-local runs during iteration; run full monorepo tests before PR
Database testing (in-memory)
Always use in-memory databases for tests. Do not use vi.mock/vi.fn to mock repository methods and do not require running database servers. The project provides embedded, in-process database engines that run the real SQL against the real schema:
- ClickHouse → chdb (
chdbpackage): An in-process ClickHouse engine via@platform/testkit. - Postgres → PGlite (
@electric-sql/pglite): An in-process Postgres via WASM via@platform/testkit.
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.
- 3d ago First seen · 112 lines · 41 tokens per session scan A d10cfba15530
testing is a skill published in the GitHub repository latitude-dev/latitude-llm (4,611 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 1,066 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
phoenix-playwright-tests
Write Playwright E2E tests for the Phoenix AI observability platform. Use when creating, updating, or debugging Playwright tests, or when the user asks about testing UI features, writing E2E tests, or automating browser interactions for Phoenix.
phoenix-pxi-playwright
Write, extend, and debug PXI Playwright E2E tests for Phoenix. Use when adding PXI agent frontend specs, authoring LLM-as-judge rubrics, asserting PXI tool use, persisting PXI test runs as Phoenix experiments, or debugging PXI E2E failures.
phoenix-client-development
Development guide for the @arizeai/phoenix-client TypeScript SDK — run and resume experiments, manage OpenTelemetry tracer providers with stack-based attach/detach, and write vitest unit and integration tests. Use when adding features to phoenix-client, debugging experiment lifecycle or provider cleanup, modifying…
testing-patterns
Testing patterns and principles. Unit, integration, mocking strategies.
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.