SpaceCat API Service is an HTTP API for working with SpaceCat data, including a server-side proxy for the Semrush AIO API and a PostgreSQL-backed data service. Developers and operators use it to access and run the Edge Delivery services data system.
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 adobe/spacecat-api-service --skill implement-e2e-testsgit clone --depth 1 https://github.com/adobe/spacecat-api-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/adobe/spacecat-api-service/implement-e2e-tests)<a href="https://agentmods.dev/skills/adobe/spacecat-api-service/implement-e2e-tests"><img src="https://agentmods.dev/badge/skills/adobe/spacecat-api-service/implement-e2e-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/adobe/spacecat-api-service/implement-e2e-tests"><img src="https://agentmods.dev/badge/skills/adobe/spacecat-api-service/implement-e2e-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 | $0.00038 | $0.01593 |
| Opus 5.5 | $0.00015 | $0.00637 |
| Sonnet 5.5 | $0.00008 | $0.00319 |
| Haiku 4.5 | $0.00004 | $0.00159 |
Grade A, and why
implement-e2e-tests 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement E2E Tests
An e2e test earns its place only if it proves something no lower layer can.
test/controllers/ mocks everything and can assert any branch cheaply;
test/it/ runs the real DB/PostgREST stack with seeded, controllable personas.
Both are cheaper and faster than e2e. If a scenario is provable at either
layer, it belongs there, not here — repeating it in e2e just builds an
ice-cream cone (top-heavy on the slow, flaky layer) instead of a pyramid.
Step 1: Map the feature and its existing coverage
Identify the endpoint set from the OpenAPI paths, src/routes/index.js, and
the controller file(s) touched. Then locate what already tests them:
test/controllers/<feature>.test.js— unit, mockedtest/it/shared/tests/<feature>.js— integration, real Postgres/PostgRESTtest/e2e/<feature>.e2e.js— e2e, if this is an enhancement to an existing feature. Read it in full before writing anything — supplement it, don't fork a parallel file.
Completion: you can point at the covering file (or "none exists yet") for every candidate scenario before triaging.
Step 2: Triage — keep only what only e2e can prove
| Keep | Why unit/IT can't prove it |
|---|---|
| This route's own auth wiring: one request without a session token, asserting the real deployed middleware rejects it | Unit mocks auth; IT pre-mints valid tokens (test/it/shared/auth.js) and never calls a route unauthenticated |
Real infra wiring: entitlement/product-access from live config, facsWrapper routing, CDN/Fastly behavior, cold start |
Mocked, or stood in for by the IT harness, everywhere else |
| One assembled consumer workflow per primary intent: the call sequence a UI feature or an AI agent would actually issue, asserting the end state a user cares about | Neither layer chains calls the way a real consumer does |
| Discard | Where it already lives |
|---|---|
| Per-field/branch 400s (missing param, wrong type, bad UUID, cap/limit boundaries) | unit — cheap to enumerate exhaustively |
| Authorization matrix across roles/orgs (403 variants) | IT — has multiple seeded personas; a live dev site usually gives you only one credential |
| Version-bump / optimistic-lock / set-difference arithmetic | IT — proven against a real DB |
Anything a sinon stub or esmock'd dependency already proves |
unit |
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 First seen · 110 lines · 38 tokens per session scan A 6e2759ef1ea0
implement-e2e-tests is a skill published in the GitHub repository adobe/spacecat-api-service (10 stars, last pushed 25d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,593 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
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.
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…
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.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.