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 instructions/idavidov13/agentic-playwright/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 | $0.04500 | $0.04500 |
| Opus 5 | $0.02250 | $0.02250 |
| Sonnet 5 | $0.00900 | $0.00900 |
| Haiku 4.5 | $0.00450 | $0.00450 |
Grade A, and why
agentic-playwright debugging.instructions.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `TimeoutError` on **navigation** | `page.goto(...) Timeout 30000ms exceeded` | Wrong URL, env not set, app down, slow first-load (cold cache) | Verify `process.env.APP_URL`; curl it; check `env/.env.${ENVIRONMENT}` | How it starts
The opening of the file, as written. The whole thing — 261 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 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.
- yesterday First seen · 261 lines · 4,500 tokens per session scan A 624899e3208e
agentic-playwright debugging.instructions.md is an instructions file published in the GitHub repository idavidov13/agentic-playwright (134 stars, last pushed 5d ago), licensed MIT. It adds 4,500 tokens to every session, about $0.0225 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 instructions, from other repositories
COG-second-brain AGENTS.md
Instructions for huytieu/COG-second-brain, covering cog: agentic second brain - universal agent commands, available commands, /onboarding, /braindump and /daily-brief.
COG-second-brain CLAUDE.md
Instructions for huytieu/COG-second-brain, covering cog second brain — framework instructions, verification harness (opt-in, off by default), visual verification (always apply, ui/ux tasks), delegation cap (always apply) and model routing — always apply.
COG-second-brain GEMINI.md
Instructions for huytieu/COG-second-brain, covering cog: agentic second brain, your role, vault structure, user profile and available skills.
agentic-config AGENTS.md
Instructions for WaterplanAI/agentic-config, covering project guidelines, environment & tooling, core rules, skill triggering and content & pii.
compare-mcp CLAUDE.md
Instructions for Cristophereasygoing927/compare-mcp, covering compare-mcp, architecture, running and key decisions.
multiagent-template CLAUDE.md
Instructions for Neftedollar/multiagent-template, covering how to start (required for every session), 1. determine mode, 2. load context (depends on mode), 3. act and workspace structure.