acp-local-runner
Skill545 starsChanged 9 months agoMITView on GitHub
Run and debug Agmente ACP end-to-end scenarios from the repo-owned e2e/scenarios/acp specs. Use when validating ACP websocket compatibility, session creation, cwd handling, reconnect flows, or reproducing ACP-only UI failures against a real local ACP backend.
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
- codex-local-cli-e2eSkill
- repeat-with-delaySkill
- upstream-protocol-drift-watchSkill
- run-agmente-codex-e2eSkill
- run-agmente-e2eSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
20 rules. About 0 are common, 14 are distinctive, and 6 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈14
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 17
Read the requested scenario from e2e/scenarios/acp/.
- Distinctive: line 18
If the user names no scenario, choose the closest match from that directory and state the choice.
- Distinctive: line 19
Treat the scenario file as the source of truth for setup, steps, assertions, and cleanup intent.
- Distinctive: line 22
Read the backend id from the scenario front matter.
- Distinctive: line 24
Use the backend file for canonical endpoint, start command, stop command, and capability notes.
- Very specific: line 27
Prefer simulator execution when the scenario target is ios-simulator.
- Very specific: line 28
Use XcodeBuildMCP tools when available for boot/build/run/log/screenshot/interaction.
- Distinctive: line 29
If simulator interaction tools are incomplete, use the best available non-editing fallback and state the limitation.
- Distinctive: line 30
Verify the backend is reachable before debugging app behavior.
- Distinctive: line 33
Follow the scenario steps in order.
- Very specific: line 35
Use the scenario assertions and e2e/assertions/common.md to judge pass/fail.
- Distinctive: line 40
Always stop the backend if this run started it.
- Very specific: line 41
Always uninstall Agmente from the simulator unless the user explicitly asks to preserve state.
- Distinctive: line 45
Do not invent ACP behavior that is not in the scenario or backend docs.
- Distinctive: line 46
Do not make the skill the source of truth for scenario semantics.
- Distinctive: line 47
Prefer protocol-level explanations over tool-level explanations in failure reports.
- Distinctive: line 48
If the scenario and backend docs disagree, treat that as repo drift and report it.
- Very specific: line 49
Treat run, execute, validate, and reproduce as execute-only requests.
- Distinctive: line 52
If the run is blocked by missing automation hooks or incomplete tooling, report the blocker and stop instead of editing the repo.
- Distinctive: line 53
Only make repository changes when the user explicitly asks to fix, stabilize, add hooks, or make the scenario executable.
≈ “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
ACP Local Runner
Overview
Execute a repo-owned ACP scenario against a real local ACP backend, capture enough logs and UI state to diagnose failures, and always clean up backend and simulator app state.
For run, execute, validate, or reproduce requests, this skill is execute-only. Use real tools to perform the scenario; do not modify repository files unless the user explicitly asks to fix, stabilize, or make the flow executable.
Workflow
- Resolve the scenario.
- Read the requested scenario from
e2e/scenarios/acp/. - If the user names no scenario, choose the closest match from that directory and state the choice.
- Treat the scenario file as the source of truth for setup, steps, assertions, and cleanup intent.
- Resolve the backend.
- Read the backend id from the scenario front matter.
- Open the matching file in
e2e/backends/. - Use the backend file for canonical endpoint, start command, stop command, and capability notes.
- Prepare execution.
- Prefer simulator execution when the scenario target is
ios-simulator. - Use XcodeBuildMCP tools when available for boot/build/run/log/screenshot/interaction.
- If simulator interaction tools are incomplete, use the best available non-editing fallback and state the limitation.
- Verify the backend is reachable before debugging app behavior.
- Run the scenario.
- Follow the scenario steps in order.
- Capture wire or console checkpoints around
initialize,session/list,session/new,session/prompt,session/load, and reconnect events when relevant. - Use the scenario assertions and
e2e/assertions/common.mdto judge pass/fail.
- Report and clean up.
- Report backend, endpoint, simulator target, scenario path, and pass/fail status.
- On failure, report the concrete broken step and the most likely root cause.
- Always stop the backend if this run started it.
- Always uninstall Agmente from the simulator unless the user explicitly asks to preserve state.
Guardrails
- Do not invent ACP behavior that is not in the scenario or backend docs.
- Do not make the skill the source of truth for scenario semantics.
- Prefer protocol-level explanations over tool-level explanations in failure reports.
- If the scenario and backend docs disagree, treat that as repo drift and report it.
- Treat
run,execute,validate, andreproduceas execute-only requests. - Agentic testing means actually running the backend, simulator, and relevant protocol tooling rather than describing manual steps.
- During execute-only runs, do not add accessibility identifiers, write harness code, patch docs, or create new tests to make the scenario pass.
- If the run is blocked by missing automation hooks or incomplete tooling, report the blocker and stop instead of editing the repo.
- Only make repository changes when the user explicitly asks to fix, stabilize, add hooks, or make the scenario executable.
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.

