run-agmente-codex-e2e
Skill545 starsChanged 9 months agoMITView on GitHub
Run Agmente iOS end-to-end tests against a local Codex app-server endpoint, validate Codex thread/turn protocol flow, and perform mandatory cleanup.
In this repository13 other files it gives its agents.
- ACPClient/AGENTS.mdAGENTS.md
- Agents.mdAGENTS.md
- Agmente/AGENTS.mdAGENTS.md
- AgmenteTests/AGENTS.mdAGENTS.md
- AgmenteUITests/AGENTS.mdAGENTS.md
- AppServerClient/AGENTS.mdAGENTS.md
- e2e/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- acp-local-runnerSkill
- codex-local-cli-e2eSkill
- repeat-with-delaySkill
- upstream-protocol-drift-watchSkill
- run-agmente-e2eSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 3 are distinctive, and 6 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill when the user asks to run Agmente E2E against OpenAI Codex app-server.
- Distinctive: line 20
Start local Codex bridge in background:
- Very specific: line 23
Use XcodeBuildMCP build_run_sim with Agmente defaults.
- Very specific: line 27
Call describe_ui before each tap.
- Very specific: line 28
Prefer tap by id or label.
- Distinctive: line 37
Do not skip cleanup.
- Very specific: line 38
Use a valid host working directory (for example /path/to/your/workspace).
- Distinctive: line 39
Do not rely on guessed coordinates from screenshots.
- Very specific: line 40
Prefer deterministic selectors and describe_ui.
≈ “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.
Files
Run Agmente Codex App-Server E2E
Use this skill when the user asks to run Agmente E2E against OpenAI Codex app-server.
Inputs
scenario:sanity(default),add-server,turn-sendport: default9000simulatorID: defaultBE205EA8-B26C-44C2-B52B-B49141678273codexCommand: defaultcodex app-server(override via first arg tostart_codex.shorCODEX_APP_SERVER_CMD)npxTag: package tag for@rebornix/stdio-to-ws(latestby default, override via third arg orAGMENTE_E2E_NPX_TAG)
Workflow
- Start local Codex bridge in background:
./.github/skills/run-agmente-codex-e2e/scripts/start_codex.sh "<codexCommand>" <port> <npxTag>
- Build and run in simulator:
- Use XcodeBuildMCP
build_run_simwith Agmente defaults.
- Use XcodeBuildMCP
- Execute UI steps:
- Follow
references/ui-checklist.md. - Set server type to
Codex App-Server. - Call
describe_uibefore each tap. - Prefer tap by
idorlabel.
- Follow
- Validate protocol behavior from bridge logs:
- Confirm sequence:
initialize->initialized->thread/list->thread/start->turn/start->turn/started->turn/completed. - Confirm streamed notifications arrive (
item/*and/orcodex/event/*).
- Confirm sequence:
- Cleanup always (success or failure):
./.github/skills/run-agmente-codex-e2e/scripts/cleanup.sh <simulatorID> <port>
Constraints
- Do not skip cleanup.
- Use a valid host working directory (for example
/path/to/your/workspace). - Do not rely on guessed coordinates from screenshots.
- Prefer deterministic selectors and
describe_ui.
References
- UI and validation checklist:
references/ui-checklist.md
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
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.

