simba-codex-lifecyclelisted

# Simba Codex Lifecycle Run this routine for implementation tasks in Simba-enabled repositories. ## Required Sequence 1. Recall relevant memory first (use the user request as query text): ```bash simba codex-recall "<user request>" ``` 2. Run status once per session: ```bash simba codex-status ``` Do not run this on every prompt. Re-run only if: - there was a long pause or major context shift, - memory actions fail unexpectedly, - you are about to finalize and want a fresh check. 3. If status reports `pending_extraction`, run: ```bash simba codex-extract ``` 4. Before final handoff, run finalize: ```bash simba codex-finalize ``` ## Finalize Inputs Prefer to include both response text and transcript path when available: ```bash simba codex-finalize --response-file /path/to/response.txt --transcript /path/to/transcript.jsonl ``` If those files are not available, still run `simba codex-finalize` as a best-effort check. If `simba` is not in PATH, use: ```bash uvx --from /Users/mahmoud/src/ai/simba simba codex-status ``` ## Output Discipline - Mention whether `codex-recall` returned relevant memories and how they informed your approach. - Mention in your final update that lifecycle checks were run. - If `codex-status` reports pending extraction, do not ignore it. Run `codex-extract` and report that action.