agentleFS
rebornixrebornix/Agmente/e2e/AGENTS.md

Agmente / e2e

AGENTS.md545 starsChanged 9 months agoMITView on GitHub

The file

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

5 rules. About 0 are common, 3 are distinctive, and 2 are 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer Markdown with front matter for scenarios and backends.

    line 14
  2. Distinctive:

    If execution is blocked by missing affordances or incomplete tooling, report the concrete blocker and stop.

    line 21
  3. Very specific:

    Keep setup/steps/assertions/cleanup in scenario files concise and behavior-focused.

    line 26
  4. Very specific:

    Update Agents.md and CLAUDE.md when changing the top-level e2e/ contract.

    line 27
  5. Distinctive:

    Update this file when changing scenario structure, backend references, or contribution rules.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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

Agmente E2E Scenarios Guide

Scope

Repository-owned end-to-end scenario specifications, reusable backend definitions, shared assertions, and contribution rules for simulator/manual protocol validation.

Ownership Boundaries

  • e2e/scenarios/ is the source of truth for user-facing E2E intent.
  • e2e/backends/ defines reusable backend launch/config metadata.
  • e2e/assertions/ defines shared assertion vocabulary to avoid restating expectations.
  • e2e/schema/ documents required front matter and section structure.
  • .agents/skills/ may help execute scenarios, but scenarios must not depend on a specific skill.

Architecture Rules

  • Prefer Markdown with front matter for scenarios and backends.
  • Scenario files should contain only scenario-specific behavior.
  • Shared launch commands, cleanup commands, and assertion wording belong in reusable docs, not copied into every scenario.
  • Skills may read scenarios to decide execution steps, but scenario files must stay valid and useful without any skill system.
  • run, execute, validate, and reproduce requests are execute-only unless the user explicitly asks to fix or stabilize the scenario.
  • Execute-only means agentic testing: use real backends, simulator or protocol tools, logs, assertions, and cleanup instead of proposing code changes.
  • During execute-only runs, do not edit app code, add automation hooks, write new tests, or patch docs to work around blockers.
  • If execution is blocked by missing affordances or incomplete tooling, report the concrete blocker and stop.

Contribution Checklist

  • Reuse an existing backend in e2e/backends/ before adding a new one.
  • Reuse shared assertion names from e2e/assertions/common.md where possible.
  • Keep setup/steps/assertions/cleanup in scenario files concise and behavior-focused.
  • Update Agents.md and CLAUDE.md when changing the top-level e2e/ contract.
  • Update this file when changing scenario structure, backend references, or contribution rules.

Required Sections

  • Front matter with scenario identity and backend/target metadata.
  • # Setup
  • # Steps
  • # Assertions
  • # Cleanup

Compatibility Notes

  • ACP scenarios should describe session/new, session/prompt, session/load, and cwd expectations in protocol terms, not tool terms.
  • Codex scenarios should describe thread/start, thread/resume, and turn expectations in protocol terms, not tool terms.
  • Simulator automation guidance belongs in skills or test harness docs, unless it is a scenario-specific precondition.

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.