grokodex-runlisted

# Grokodex Run Run a **headless local Grok agent** task through the Grokodex MCP bridge (Codex, Claude Code, or other MCP hosts). ## When to use - User wants Grok’s second opinion or implementation help - Hard bugs / multi-file refactors better handled by a peer agent - Explicit “run Grok / ask Grok / delegate to Grok” requests - **Not** for pure read-only review of diffs (findings only, no edits) → use `grokodex-review` (`profile=review`) - **Not** for design challenge / approach critique only → use `grokodex-critique` (`profile=critique`) - Do **not** use bare `grok_run` (no profile) when the user only wants review without edits - Not for pure image gen → use `grokodex-imagine` - Not for pure X/Twitter search → use `grokodex-x-search` - Not for install/login diagnosis → use `grokodex-setup` ## Tool preference (critical) 1. **Always call MCP tool `grok_run`** (logical name). On Claude Code the UI may show a prefixed name such as `mcp__…__grok_run` — use whatever `/mcp` lists for this server; still treat it as `grok_run`. 2. **Forbidden:** any terminal / shell tool to execute `grok` directly for the task. 3. **Exception:** only `grokodex-setup` install/login guidance may mention shell `grok` (install script / `grok login`). Never use shell as a bypass of `grok_run`. Bridge serializes Grok processes; avoid firing parallel `grok_run` calls that both write the same repo. Prefer one active Grok worker at a time. ## Default permissions - **Do not pass `permission_mode`** u