agentmods.dev

phoenix_test_playwright AGENTS.md

Project-specific development instructions for an Elixir application and its Playwright browser-testing compatibility suite. Playwright is a tool for automating real browser interactions.

In plain words
What is it for?
Use it while changing the project to run targeted tests, perform the final checks, update documentation and the changelog, and test browser transport changes.
Why use it?
It tells contributors which tool versions and checks to use, where browser-specific tests belong, and how to avoid unnecessary changes to copied upstream tests.

Instructions file for CodexOpenCode

86 5d ago A scan 265 tokens original MIT
View the source file ftes/phoenix_test_playwright
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/ftes/phoenix_test_playwright/agents-md
Clone the repo
git clone --depth 1 https://github.com/ftes/phoenix_test_playwright

Made for: Codex, OpenCode.

Per session 265 This file is loaded in full into every session.
When invoked 265 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 $0.00265 $0.00265
Opus 5 $0.00133 $0.00133
Sonnet 5 $0.00053 $0.00053
Haiku 4.5 $0.00026 $0.00026

Measured 2d ago against content hash ab940b0fd315, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phoenix_test_playwright AGENTS.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.

AGENTS.md · 17 lines

What it actually says

Dev

  • Use tool versions from .tool-versions; prefer mise exec -- <command> (for example mise exec -- mix check).
  • If your shell is already activated by mise/direnv, plain mix ... commands are fine.
  • Run targeted tests often while changing files.
  • When feature is complete run mix check.
  • When feature is complete, update CHANGELOG.md.
  • Always keep docs up to date (exdoc @doc + @moduledoc, README.md)
  • If you changed browser transport / websocket behavior, also run mix test.websocket.

phoenix_test upstream compatibility

  • test/phoenix_test/upstream/ is a mirror of upstream phoenix_test tests and is used as a compatibility suite.
  • Do not add new Playwright-specific behavior tests under test/phoenix_test/upstream/.
  • Put Playwright-only behavior tests in test/phoenix_test/playwright_test.exs (or other non-upstream/ test files).
  • test/support/upstream/web_app/ is also copied from upstream and should be changed as little as possible.
  • If you must change an upstream-mirrored file, keep the delta minimal and document why.
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 · 17 lines · 265 tokens per session scan A ab940b0fd315

Subscribe to this mod's changes

phoenix_test_playwright AGENTS.md is an instructions file published in the GitHub repository ftes/phoenix_test_playwright (86 stars, last pushed 5d ago), licensed MIT. It adds 265 tokens to every session, about $0.0013 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.

Git and workflowTestingWriting and docsliveviewphoenixplaywright
Related

Other instructions, from other repositories

playwright CLAUDE.md

Claude Code instructions for microsoft/playwright, covering monorepo packages, browser packages, tooling packages, key directories and build.

microsoft/playwright · 1,902 tokens

playwriter AGENTS.md

Instructions for remorses/playwriter, covering backward compatibility, architecture, development, running mcp locally and running cli locally.

remorses/playwriter · 11,237 tokens

dembrandt CLAUDE.md

Claude Code instructions for dembrandt/dembrandt, covering claude.md, system instruction, development commands, running the tool and testing.

dembrandt/dembrandt · 1,311 tokens

dev-browser AGENTS.md

Instructions for SawyerHood/dev-browser, covering claude.md, tooling and validation.

SawyerHood/dev-browser · 247 tokens

playwright-rust CLAUDE.md

Instructions for padamson/playwright-rust, covering claude.md, project, repository layout, skills (procedural reference) and documentation hierarchy.

padamson/playwright-rust · 3,255 tokens

sveltest AGENTS.md

Instructions for spences10/sveltest, covering agents.md, unbreakable rules, essential commands, development and testing.

spences10/sveltest · 1,850 tokens