chore(mma): Checkpoint progress on visual simulation and UI refresh before sub-agent delegation

mma-orchestrator/SKILL.md

@@ -15,11 +15,13 @@ To ensure proper environment handling and logging, you MUST NOT call the `gemini
 
 ## 1. The Tier 3 Worker (Execution)
 When performing code modifications or implementing specific requirements:
-1. **DO NOT** perform large code writes yourself.
-2. **DO** construct a single, highly specific prompt with a clear objective.
-3. **DO** spawn a Tier 3 Worker.
+1. **Pre-Delegation Checkpoint:** For dangerous or non-trivial changes, ALWAYS stage your changes (`git add .`) or commit before delegating to a Tier 3 Worker. If the worker fails or runs `git restore`, you will lose all prior AI iterations for that file if it wasn't staged/committed.
+2. **DO NOT** perform large code writes yourself.
+3. **DO** construct a single, highly specific prompt with a clear objective.
+4. **DO** spawn a Tier 3 Worker.
    *Command:* `uv run python scripts/mma_exec.py --role tier3-worker "Implement [SPECIFIC_INSTRUCTION] in [FILE_PATH]. Follow TDD and return success status or code changes."`
-4. The Tier 3 Worker is stateless and has tool access for file I/O. 
+5. **Handling Repeated Failures:** If a Tier 3 Worker fails multiple times on the same task, it may lack the necessary capability. You must track failures and retry with `--failure-count <N>` (e.g., `--failure-count 2`). This tells `mma_exec.py` to escalate the sub-agent to a more powerful reasoning model (like `gemini-3-flash`).
+6. The Tier 3 Worker is stateless and has tool access for file I/O. 
 
 ## 2. The Tier 4 QA Agent (Diagnostics)
 If you run a test or command that fails with a significant error or large traceback: