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/page-objectsgit 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 | $0.02940 | $0.02940 |
| Opus 5 | $0.01470 | $0.01470 |
| Sonnet 5 | $0.00588 | $0.00588 |
| Haiku 4.5 | $0.00294 | $0.00294 |
Grade A, and why
agentic-playwright page-objects.instructions.md 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 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.
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 — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Page Object Model
Critical
- Locators are
getaccessors returningLocator. This is a style/readability convention — Playwright'sLocatoris lazy either way (it only queries the DOM when an action runs), sogetvsreadonlyfield behave identically at runtime. Usegetfor consistency with the rest of the scaffold. - Constructor uses
private readonly page: Page. No other visibility modifiers, no alternative DI patterns. - Page objects import
expect, Locator, Pagefrom@playwright/test— never fromfixtures/pom/test-options.ts(that's for spec files and fixtures). - JSDoc rules:
- Forbidden on locator getters and on any method that returns a
Locator. Names are self-documenting. - Required (with
@paramand@returns) on every action method and every verification method. - Allowed on component fields (e.g.
readonly nav: NavigationComponent) — these are not locators.
- Forbidden on locator getters and on any method that returns a
- Three locator sections when the page has forms or CRUD: interactive-element locators, feedback/validation-message locators, action methods. Feedback locators are not optional — see the
selectorsskill. - Feedback/message strings come from
enums/{area}/*(e.g.Messages.LOGIN_ERROR). Never hardcoded strings insidegetByText(...). - NEVER
page.waitForTimeout(...)inside a page object. Use web-first assertions (await expect(locator).toBeVisible()) orpage.waitForResponse(...). - Exploration with
playwright-cliis mandatory before writing any locators (see theselectorsskill's Exploration-First Workflow). No guessing from wireframes, docs, or screenshots. If the app is unavailable, stop and say so — never ship placeholder locators. - Register every new page object as a fixture in
fixtures/pom/page-object-fixture.ts. Tests consume page objects through the fixture, never vianew PageObject(page).
File Locations
{area}is a placeholder. Before creating or referencing any path below, runls pages/to discover the real subdirectory names in this repo (e.g.,front-office,back-office) and use those instead.
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 · 289 lines · 2,940 tokens per session scan A 3c6aade611b9
agentic-playwright page-objects.instructions.md is an instructions file published in the GitHub repository idavidov13/agentic-playwright (134 stars, last pushed 5d ago), licensed MIT. It adds 2,940 tokens to every session, about $0.0147 per session on Opus 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 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.