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/debuggingnpx skills add idavidov13/agentic-playwright --skill debugginggit 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 | $0.00179 | $0.04759 |
| Opus 5 | $0.00089 | $0.02380 |
| Sonnet 5 | $0.00036 | $0.00952 |
| Haiku 4.5 | $0.00018 | $0.00476 |
Grade A, and why
debugging scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `TimeoutError` on **navigation** | `page.goto(...) Timeout 30000ms exceeded` | Wrong URL, env not set, app down, slow first-load (cold cache) | Verify `process.env.APP_URL`; curl it; check `env/.env.${ENVIRONMENT}` | How it starts
The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging
When a test fails, you investigate first and fix second. This skill is the canonical entry point for after a test breaks — what to look at, in what order, with which Playwright tool.
Critical
- ALWAYS read the failure message first. Playwright errors identify the failing locator, assertion, timeout type, and source line. Skim the message before changing any code or guessing.
- NEVER suppress a failure. Don't add
test.skipwithout// FIXME: <ticket-url>, don't loosen an assertion, don't bump timeouts to make a flake pass, don'ttry/catchanexpectto swallow it. If the API genuinely misbehaves, follow theapi-testingPhase 7 behaviour-mismatch protocol. - NEVER add
page.waitForTimeout(...)to "fix" a timing issue. Hard waits hide the real cause. Use a web-first assertion (await expect(locator).toBeVisible()) orpage.waitForResponse(...)instead. - NEVER push a fix you can't reproduce locally. Pull the CI trace and replay it before believing the issue is resolved.
traceis opt-in for retries. This scaffold'splaywright.config.tssetstrace: 'on-first-retry'. Locallyretries: 0, so traces are NOT captured by default. To get a trace locally, either run with--trace on(or--trace retain-on-failure) or use UI Mode (npm run test:ui).- Prefer UI Mode (
npm run test:ui) for interactive debugging. It's the fastest feedback loop — every test step is replayable, locators are live-pickable, the DOM at each step is inspectable. Reach for it before the Inspector orconsole.log. - Re-run multiple times before declaring a flake fixed. A passing run after one fix is not enough; aim for at least 5 consecutive green runs of the affected test before closing the issue.
- Keep
forbidOnly: !!process.env.CIin mind.test.only(...)is your friend locally for narrowing — but do not commit it. CI will fail the build. - Re-run lint and the full affected file after each fix —
npx eslint .andnpx playwright test <file>before moving on.
What ships with it
2 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 · 265 lines · 179 tokens per session scan A c89a87561f34
debugging is a skill published in the GitHub repository idavidov13/agentic-playwright (139 stars, last pushed 5d ago), licensed MIT. It adds 179 tokens to every session and 4,759 once invoked, about $0.0009 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…