agentleFS
rebornixrebornix/Agmente/.agents/skills/codex-local-cli-e2e/SKILL.md

codex-local-cli-e2e

Skill545 starsChanged 9 months agoMITView on GitHub

Run and debug Agmente iOS end-to-end tests against a real local Codex CLI app-server instance. Use when validating Codex websocket/protocol compatibility, connect/initialize/thread flows, or reproducing Codex-only UI test failures with an actual local Codex server.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Run Agmente's Codex UI E2E test against a real local codex app-server, using the repo-owned scenario spec as the source of truth, collect …

    line 10
  2. Very specific:

    Use references/agmente-codex-e2e-contract.md only for the UI-test environment-variable harness contract.

    line 20
  3. Distinctive:

    Start or verify server.

    line 22
  4. Very specific:

    If managed server, start the command and wait until the endpoint port is reachable.

    line 23
  5. Very specific:

    If existing server, verify reachability before running tests.

    line 24
  6. Distinctive:

    Run only the Codex UI E2E test.

    line 26
  7. Very specific:

    Read .xcresult details when xcodebuild is not explicit.

    line 35
  8. Distinctive:

    Stop app-server if this run started it.

    line 39
  9. Distinctive:

    Use the bundled script for deterministic runs:

    line 46

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
SKILL.md

Codex Local CLI E2E

Overview

Run Agmente's Codex UI E2E test against a real local codex app-server, using the repo-owned scenario spec as the source of truth, collect actionable failure details, and always clean up simulator/app-server state.

Workflow

  1. Resolve run inputs.
  • Require endpoint (for example ws://127.0.0.1:8788) and simulator UDID.
  • Decide run mode:
    • existing server: server already running.
    • managed server: start server with a provided command and stop it during cleanup.
  • Read e2e/scenarios/codex/local-cli-smoke.md.
  • Use references/agmente-codex-e2e-contract.md only for the UI-test environment-variable harness contract.
  1. Start or verify server.
  • If managed server, start the command and wait until the endpoint port is reachable.
  • If existing server, verify reachability before running tests.
  1. Run only the Codex UI E2E test.
  • Export:
    • AGMENTE_E2E_CODEX_ENABLED=1
    • AGMENTE_E2E_CODEX_ENDPOINT=<endpoint>
  • Execute targeted test only:
    • AgmenteUITests/AgmenteUITests/testCodexDirectWebSocketConnectInitializeAndSessionFlow
  1. On failure, extract root cause.
  • Parse xcodebuild output for the failing test and assertion.
  • Read .xcresult details when xcodebuild is not explicit.
  • Include failing file/line and endpoint/simulator context in the report.
  1. Always clean up.
  • Stop app-server if this run started it.
  • Uninstall app from simulator:
    • xcrun simctl uninstall <UDID> com.example.Agmente
  • Optionally shut simulator down if requested.

Preferred Execution

Use the bundled script for deterministic runs:

  • scripts/run_codex_local_e2e.sh

Managed-server example:

scripts/run_codex_local_e2e.sh \
  --endpoint ws://127.0.0.1:8788 \
  --udid <SIMULATOR_UDID> \
  --start-codex-cmd "codex app-server --listen ws://127.0.0.1:8788"

Existing-server example:

scripts/run_codex_local_e2e.sh \
  --endpoint ws://127.0.0.1:8788 \
  --udid <SIMULATOR_UDID>

Reporting Requirements

Always report:

  • Endpoint used.
  • Simulator UDID used.
  • Pass/fail status.
  • Failing assertion and file/line (if failed).
  • Paths to xcodebuild log and Codex server log.

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.