agentleFS
Sign inStart free
anhtesteranhtester/codex-testing-kit/AGENTS.md

codex-testing-kit

AGENTS.md28 starsChanged 4 months agoMITView on GitHub

The file

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

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    Use repository skills from .agents/skills when the request matches their description or when the user invokes a skill with $skill-name.

    line 5
  2. Distinctive:

    Read only the relevant rule files before implementing or reviewing automation code:

    line 6
  3. Distinctive:

    Prefer stable semantic locators and smart waits.

    line 27
  4. Distinctive:

    Keep test data unique, traceable, deterministic when seeded, and free of real personal information.

    line 28

≈ “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

Codex workspace guidance

QA automation resources

  • Use repository skills from .agents/skills when the request matches their description or when the user invokes a skill with $skill-name.
  • Read only the relevant rule files before implementing or reviewing automation code:
    • .agents/rules/automation_rules.md for shared automation and test-data conventions.
    • .agents/rules/api_rules.md for API automation and OWASP security rules.
    • .agents/rules/locator_strategy.md for locator selection.
    • .agents/rules/playwright_rules.md for Playwright work.
    • .agents/rules/selenium_rules.md for Selenium work.
    • .agents/rules/appium_rules.md for Appium work.
    • .agents/rules/delivery_checklist.md before completing automation work.
  • Invoke workflow skills with $ and kebab-case, for example $generate-locator or $analyze-flaky-tests.

Legacy tool-name compatibility

  • Interpret tool names retained in migrated instructions by intent and use the callable Codex equivalent in the current session.
  • Map view_file to a read-only filesystem command, write_to_file/replace_file_content to apply_patch, and run_command/command_status to shell execution and its wait mechanism.
  • Map read_url_content to the available web or in-app browser capability.
  • Map conceptual browser_* steps to the installed in-app browser skill and its current callable tools; do not invent unavailable tool calls.

Working expectations

  • Communicate and report results in concise, clear Vietnamese.
  • Preserve the current local code state. Do not run state-changing Git commands such as git pull, git checkout, git merge, git rebase, or git reset unless the user explicitly requests them. Read-only Git inspection is allowed.
  • Prefer stable semantic locators and smart waits; do not introduce fixed sleeps unless the user explicitly requires them.
  • Keep test data unique, traceable, deterministic when seeded, and free of real personal information.
  • Validate generated automation with the narrowest relevant test, lint, or compile command available in the target project.

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