Borrowing it
Nothing to install: this file belongs to chirino/memory-service. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chirino/memory-service/main/.skills/site-tests/SKILL.mdgit clone --depth 1 https://github.com/chirino/memory-serviceWrote 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/chirino/memory-service/site-tests)<a href="https://agentmods.dev/skills/chirino/memory-service/site-tests"><img src="https://agentmods.dev/badge/skills/chirino/memory-service/site-tests/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/chirino/memory-service/site-tests"><img src="https://agentmods.dev/badge/skills/chirino/memory-service/site-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00109 | $0.03516 |
| Opus 5.5 | $0.00044 | $0.01406 |
| Sonnet 5.5 | $0.00022 | $0.00703 |
| Haiku 4.5 | $0.00011 | $0.00352 |
Grade A, and why
site-tests scanned grade A with 1 finding 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 15d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
description: "Use when editing documentation pages that contain <TestScenario>/<CurlTest> (site/src/pages/docs/**/*.mdx), doc checkpoint apps (*/examples/**/doc-checkpoints/**), internal/sitebdd/**, OpenAI mock fixtures How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site Doc Tests
Tutorial pages are executable. Each <TestScenario checkpoint="..."> builds and starts a checkpoint app, then runs the curl commands on the page and checks the assertions.
Pipeline
cd site && npm run build:site/src/components/TestScenario.astrocollects every```bashblock inside a<TestScenario>(not only the ones in<CurlTest>), plus thestepsof the<CurlTest>that follows each one, and writes them tosite/dist/test-scenarios.json. Blocks that share a(checkpoint, page)pair are merged.TestSiteDocs(internal/sitebdd/site_test.go) loads that file.scenarios.gogenerates one feature per page in a temp dir, tagged@<framework>,@wave_N,@checkpoint_<path>. Never edit generated features; edit the MDX.- Before any scenario runs, it runs
clean installfor the Quarkus extension deployment and Spring Boot starter (Java pages) anduv buildforpython/langchain(Python pages). - godog runs the scenarios against one shared in-process Memory Service (Postgres via testcontainers, so Docker is required) plus an in-process OpenAI/OIDC mock (
mock*.go). Pages whose route contains/unix-domain-socketsuse a second, SQLite-backed server that listens on a Unix socket. - Waves (
wave_coordinator.go): up tositeScenarioConcurrency()scenarios build and start together. No curl runs until every wave member is running or has exited. The next wave starts only after the current one drains. A checkpoint directory never appears twice in one wave.
Running
task test:site > site-test.log 2>&1 # everything; grep the log for failures
GODOG_TAGS='@quarkus' task test:site -- -count=1 # args after -- go to go test
GODOG_TAGS='@python-langchain && @checkpoint_python_examples_langchain_doc_checkpoints_05_response_resumption' task test:site -- -count=1
go build -tags='site_tests sqlite_fts5' ./internal/sitebdd/ # compile check, no Docker
go test -tags='site_tests sqlite_fts5' ./internal/sitebdd/ -run 'TestDocs' -count=1 # MDX lint only, no Docker
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.
- 15d ago Changed 574b9bbdfcb1
- 1mo ago First seen · 124 lines · 109 tokens per session scan A f2b23f7b8e96
site-tests is a skill published in the GitHub repository chirino/memory-service (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 109 tokens to every session and 3,516 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.