agentic-playwright common-tasks.instructions.md

A guide for choosing and filling in prompt templates that generate Playwright test artifacts. It explains how to identify the task type, resolve the correct project paths, and verify the generated result.

In plain words
What is it for?
Use it when generating Playwright code from prompts, especially when the task needs a page object, API test, fixture, schema, or other project artifact.
Why use it?
It prevents templates from being filled with guessed folder names or incomplete project details. It also points the agent to the wider rules and specialized instructions it must follow.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/idavidov13/agentic-playwright/common-tasks
Clone the repo
git clone --depth 1 https://github.com/idavidov13/agentic-playwright

Made for: GitHub Copilot.

Per session 5,109 This file is loaded in full into every session.
When invoked 5,109 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.05109 $0.05109
Opus 5 $0.02554 $0.02554
Sonnet 5 $0.01022 $0.01022
Haiku 4.5 $0.00511 $0.00511

Measured 2d ago against content hash b65ff474b856, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-playwright common-tasks.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.

.github/instructions/common-tasks.instructions.md · 438 lines

How it starts

The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Prompt Templates for Agentic Playwright

Codegen sub-router. Owns prompt templates per artifact type and the post-generation verification checklist. Plugs into ai-native-workflow Phase 2 (Route) for codegen intents.

For the 8-phase workflow see ai-native-workflow/SKILL.md. For worked examples and troubleshooting see this skill's references/.

Critical

These rules are unique to template usage. All other rules (selectors, waits, types, Zod strictness, response validation, tags, fixtures, JSDoc, no-XPath, no-hardcoded-strings, etc.) live in the Constitution (the always-loaded MUST/SHOULD/WON'T tables wrapping these instructions) and the leaf skills (api-testing, page-objects, selectors, test-standards, data-strategy, type-safety, fixtures, enums). Re-read the Constitution + the matching leaf skill's Critical block before generating from any template here.

  • Resolve {area} first. Every template contains {area} as a placeholder. Run the matching ls (ls pages/, ls tests/, ls fixtures/api/schemas/, ls test-data/factories/, ls test-data/static/, ls enums/) and substitute the real folder name before filling the template. Do not guess.
  • Templates are starters, not substitutes. Each template is a 10-15 line scaffold. The leaf skill listed for the category owns the deep rules — load it and follow it end-to-end. Never reimplement a leaf skill's rules inline in your prompt.
  • Walk the verification checklist (below) after generating. It is the canonical post-codegen audit; the leaf skills point here for it.

Instructions

Phase 1: Identify the task category and resolve paths

Match the user's request to one row, then run the ls commands the row's templates need.

Category Template section Specialized skill(s) ls to run before filling
Page object / component Page Object Tasks page-objects, selectors, playwright-cli ls pages/
Functional / E2E test Test Tasks test-standards, data-strategy ls tests/, ls test-data/factories/
API test Test Tasks → Add API Test api-testing, test-standards ls tests/, ls fixtures/api/schemas/, ls enums/
Zod response schema API Schema Tasks api-testing, type-safety ls fixtures/api/schemas/
Data factory Data Factory Tasks data-strategy, type-safety ls test-data/factories/
Static test data Data Factory Tasks → Static Test Data data-strategy, api-testing ls test-data/static/
Fixture (POM / helper) Fixture Tasks fixtures, helpers (no path placeholder)
UI component Component Tasks page-objects, selectors (no path placeholder)

Read the full file on GitHub · 438 lines

Changes

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.

  1. 2d ago First seen · 438 lines · 5,109 tokens per session scan A b65ff474b856

Subscribe to this mod's changes

agentic-playwright common-tasks.instructions.md is an instructions file published in the GitHub repository idavidov13/agentic-playwright (139 stars, last pushed 6d ago), licensed MIT. It adds 5,109 tokens to every session, about $0.0255 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.