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/idavidov13/agentic-playwright/api-testingnpx skills add idavidov13/agentic-playwright --skill api-testinggit clone --depth 1 https://github.com/idavidov13/agentic-playwrightWhat 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 | $0.00132 | $0.05007 |
| Opus 5 | $0.00066 | $0.02504 |
| Sonnet 5 | $0.00026 | $0.01001 |
| Haiku 4.5 | $0.00013 | $0.00501 |
Grade A, and why
api-testing 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 2d 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.
- **Do NOT** curl the endpoint first to "see what it returns" and then write schemas that match reality. How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API Testing
Critical
These rules are non-negotiable. Violating any of them breaks the scaffold's contract.
- NEVER hardcode API URLs, access tokens, emails, passwords, or endpoint paths. The only allowed sources of truth are
process.env.*(for URLs and credentials) and theenums/{area}/*enums (for endpoint paths, e.g.ApiEndpoints.LOGIN). - ALWAYS validate API response bodies with Zod using the exact assertion pattern
expect(SchemaName.parse(body)).toBeTruthy();. Type generics alone are not enough, andschema.parse(body)without theexpect(...).toBeTruthy()wrapper is not enough. - ALWAYS wrap each API call in
test.step()when a test contains more than one API call. - NEVER silently drop a test because the API misbehaves. Write the test as the spec says, wrap it in
test.skip, and add a// FIXME: <ticket-url>comment. - NEVER stop at
{}empty-body validation. Every request-body endpoint requires per-field omission and per-field invalid-type tests. - ALWAYS fuzz path parameters with the invalid-format data-driven loop — regardless of whether OpenAPI mentions it.
- ALWAYS use the
apiRequestfixture directly in tests. Only promote to a helper fixture when the same setup/teardown is reused across 3+ test files.
Instructions
Phase 1: Source the contract (documentation first, exploration only as fallback)
The API contract — not observed behavior — is the source of truth for schemas and tests.
- If OpenAPI / Swagger / equivalent documentation exists (the normal case):
- Build schemas and tests strictly from the documented contract: field names, types, required vs optional, nullability, status codes, error shapes.
- Do NOT curl the endpoint first to "see what it returns" and then write schemas that match reality.
- If, during test execution, the actual response disagrees with the documentation (missing field, wrong type, wrong status code, extra field), that is a bug to report, not a reason to loosen the schema. Handle it via Phase 7 (
test.skip+// FIXME: <ticket-url>).
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 373 lines · 132 tokens per session scan A 8682a35635d2
api-testing is a skill published in the GitHub repository idavidov13/agentic-playwright (134 stars, last pushed 5d ago), licensed MIT. It adds 132 tokens to every session and 5,007 once invoked, about $0.0007 per session on Opus 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 2026-08-30.
Other skills, from other repositories
vindicate
Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…
editorial-illustrations
Generate meaning-carrying editorial data-illustrations in the monotykamary / Linear aesthetic (near-black grayscale, Inter display + mono labels, hairline framed figures) with a single coral accent. This is a GENERATIVE GUIDE, not a template gallery: it teaches the "claim -> geometry" method so any session can invent…
data-forms
Pick the right way to represent a dataset so a reader gets the finding in three seconds — a catalog of 20+ chart and diagram forms with when-to-use and failure modes, plus the encoding decisions that make any of them readable (takeaway headline, direct labels, kill the axis, highlight-and-mute, show the caveat).…
product-ui-taste
Anti-slop skill for PRODUCT UI - dashboards, data tables, forms, multi-step flows, settings, list/detail, app shells. The agent reads the surface, budgets the frame first, and ships dense interfaces that are correct at every edge case (overflow, long labels, empty/error/loading states, i18n expansion, keyboard/a11y).…
review-cockpit
Produce and continuously maintain ONE living review document for a multi-item session — a cockpit header (Progress checklist, Working folder, Context) plus per-item review cards that you approve or request changes on directly in the doc or side panel. Use whenever a session has multiple deliverables you need to…
closed-loop
Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper…