// Use when the user starts an interactive-mode request with `/meow-execute`; execute script, data, automation, or artifact work and append an execution handoff.
Heavy-ceremony orchestration for big work — research, planning, adversarial review, phased implementation, audit, delivery. Use when the user says "epic", "long task", "build this end to end", or wants a feature that runs all night.
Use when the user starts an interactive-mode request with `/meow-plan`; use mfl to update/discover the thread, launch a plan stage agent when needed, and create the matching proposal without editing production code.
Use when the user starts an interactive-mode request with `/meow-archive`; archive or delete the current MeowFlow thread and proposal.
Use when the user starts an interactive-mode request with `/meow-code`; implement the current MeowFlow plan and append a code handoff.
Use when the user starts an interactive-mode request with `/meow-flow` or `/mfl`; coordinate staged MeowFlow agents through mfl thread state, thread updates, mfl-run stage launches, and handoffs.
Use when the user starts an interactive-mode request with `/meow-review`; review current MeowFlow changes and append a review handoff.
| name | meow-execute |
| description | Use when the user starts an interactive-mode request with `/meow-execute`; execute script, data, automation, or artifact work and append an execution handoff. |
Run the execute stage for a MeowFlow thread.
Follow the core meow-flow workflow for thread discovery, worktree rules,
status checks, and handoffs before applying execution-specific behavior.
When running inside a stage agent:
mfl agent update-self.mfl status.mfl thread status <id> --no-color.mfl handoff get -n 5.Strip the /meow-execute prefix. Treat remaining text as the execution
objective.
For dataset generation or maintenance, use meow-dataset.
Create or update reproducible scripts, automation, validators, or summary artifacts as required by the request.
Prefer TypeScript for repository-local scripts when the repo is a TypeScript workspace.
Run the smallest validation that proves the execution artifact works.
Before finishing, append a compact handoff:
mfl handoff append --stage execute "created script X; output Y; validation Z"
Finish with changed artifacts, commands run, output locations, and the next
suggested command, usually /mfl validate.