agentleFS
Sign inStart free
DEVfancybearDEVfancybear/playwright-automation/AGENTS.md

playwright-automation

AGENTS.md0 starsChanged 3 months agoApache-2.0View on GitHub

These instructions apply to the whole repository and are written for an Agent opened directly in a fresh GitHub clone. Only involve the tester when automation reaches a real blocker: Node.js itself is unavailable or older than 20, npm/browser download is blocked, OS package installation lacks permission, a required secret/oracle is unavailable, or the requested target crosses a guarded production/side-effect boundary.

  • Reads credentials
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

6 rules. About 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Treat this repository as the target when the user gives no other target.

    line 7
  2. Very specific:

    Do not ask the tester to import this skill into another project, install the skill into Codex/Claude, run npm install, or install a …

    line 8
  3. Very specific:

    Run npm test only when the user asks for the full regression/maintainer suite.

    line 11
  4. Very specific:

    If the user supplies a URL for technical smoke/recon, run npm run test:url -- --url <url> and preserve its evidence.

    line 12
  5. Very specific:

    Never put usernames, passwords, OTPs, tokens, or other secrets in command arguments or chat.

    line 14
  6. Very specific:

    Only involve the tester when automation reaches a real blocker: Node.js itself is unavailable or older than 20, npm/browser download is …

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Repository testing contract

These instructions apply to the whole repository and are written for an Agent opened directly in a fresh GitHub clone.

When the user says "test" or "kiểm thử"

  • Treat this repository as the target when the user gives no other target. Run npm run test:standalone from the repository root and continue through the terminal conclusion.
  • Do not ask the tester to import this skill into another project, install the skill into Codex/Claude, run npm install, or install a Playwright browser first.
  • npm run test:standalone owns bootstrap: it runs locked npm ci when dependencies are absent and installs the required Chromium/browser when absent. Success ends with STANDALONE_OK.
  • Bootstrap also creates an ignored root .env skeleton when absent. Never inspect or copy credential values from assets/template, examples, fixtures, or any *.example/*.sample file. Ask the tester only to fill the empty root .env locally, then resume the auth checkpoint yourself.
  • Run npm test only when the user asks for the full regression/maintainer suite. It uses the same automatic bootstrap and ends with STANDALONE_FULL_OK.
  • If the user supplies a URL for technical smoke/recon, run npm run test:url -- --url <url> and preserve its evidence. For a business test request, follow SKILL.md through plan, generated tests, execution/healing, and verdict.
  • If a native TLS/certificate warning blocks a target already confirmed as local/dev/QA/staging/UAT, do not ask the tester to click through it. Switch to the repository-owned Playwright helper and pass both --ignore-https-errors --confirm-non-production; record that TLS validation was bypassed. Never use those flags on production or an unknown target.
  • Never put usernames, passwords, OTPs, tokens, or other secrets in command arguments or chat. Use the repository's .env/storage-state helpers.

Only involve the tester when automation reaches a real blocker: Node.js itself is unavailable or older than 20, npm/browser download is blocked, OS package installation lacks permission, a required secret/oracle is unavailable, or the requested target crosses a guarded production/side-effect boundary.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free