Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasnpx agentmods add skills/tahirraufkeeyu/software-development-agent-stack--sdas/api-test-generatorWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/api-test-generator)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/api-test-generator"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/api-test-generator/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/tahirraufkeeyu/software-development-agent-stack--sdas/api-test-generator"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/api-test-generator.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 | $0.00074 | $0.02195 |
| Opus 5.5 | $0.00030 | $0.00878 |
| Sonnet 5.5 | $0.00015 | $0.00439 |
| Haiku 4.5 | $0.00007 | $0.00219 |
Grade A, and why
api-test-generator 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Invoke this skill when:
- A team maintains an OpenAPI 3.0 / 3.1 document (
openapi.yaml,openapi.json). - CI needs a contract-drift guard that fails when responses diverge from the spec.
- You want property-based fuzzing (Schemathesis) without hand-writing input permutations.
- You need a fast port of the OpenAPI spec into an existing Java/Node test project.
Do NOT use when: the service has no machine-readable spec (write OpenAPI first); the flow is multi-step UI interaction (use e2e-test-generator); you need a load test (use performance-test or k6/Gatling — outside scope).
Inputs
spec(required): Path or URL to OpenAPI 3.x document.target(required):schemathesis,rest-assured, orsupertest.base_url(required): Origin to test against, e.g.https://staging.example.com/api.auth(optional):{ type: "bearer" | "apiKey" | "basic", env: "TEST_TOKEN" }. Default bearer fromTEST_TOKEN.rate_limit_threshold(optional): Requests/second to use in rate-limit test. Default20.out_dir(optional): Where to write tests. Defaults per target:tests/contract/,src/test/java/contract/,test/api/.
Outputs
- For
schemathesis: apytestmoduletest_contract.py, aconftest.pywith auth fixture, and a shell command to invoke via CLI. - For
rest-assured: one Java class per tag in the spec plus aBaseApiTestwith auth setup. - For
supertest: one.test.tsper resource with Jest/Vitest describe blocks. - A coverage report mapping each (path, method, response code) in the spec to a generated test.
Tool dependencies
Read,Write,Grep,Glob(always).WebFetchwhenspecis a URL.- For
schemathesis: user must havepip install schemathesis pytestin their test env. - For
rest-assured: Maven/Gradle dependencyio.rest-assured:rest-assured:5.x. - For
supertest:npm i -D supertest @types/supertest jest ajv(or vitest).
Procedure
- Load the spec. If URL, fetch. Parse YAML/JSON. Extract: servers, securitySchemes, paths, operationIds, tags, request/response schemas.
- Bucket endpoints. Group by tag; one file per tag (rest-assured, supertest) or a single pytest module (schemathesis).
- Resolve auth. Map
securitySchemesto an auth fixture that reads the token fromauth.env. - Generate positive tests. For each operation, produce a request with a minimal valid body (schemathesis does this automatically; for manual targets, instantiate from
exampleor required-fields-only). - Generate negative tests.
- Missing required fields → expect
400. - Wrong type (
stringwhereinteger) → expect400or422. - Unauthenticated call → expect
401. - Wrong scope / forbidden → expect
403. - Unknown resource id → expect
404.
- Missing required fields → expect
- Generate rate-limit test. Fire
rate_limit_threshold * 2requests in a burst against a GET endpoint; assert at least one429and thatRetry-Afteris present. - Validate every response against schema. Use
schemathesisbuilt-in validation,rest-assured.matchesJsonSchema, orajvin supertest. - Emit a coverage table. Markdown file listing endpoint × response code × covered/uncovered.
- Write CI snippet. A
Makefiletarget or GitHub Actions step to run the suite on every PR.
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 · 208 lines · 74 tokens per session scan A 877defce9af9
api-test-generator is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (19 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 2,195 once invoked, about $0.0003 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 2026-08-30.
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.