grok-plugin-cc — Grok inside Claude Code
- JavaScript
- Node.js
- Claude Code Plugin
- Grok CLI
- headless mode
A Claude Code port of the official openai/codex-plugin-cc surface, adapted to drive the local Grok CLI headless mode. It mirrors the same bounded review, adversarial-review, rescue, transfer, status, result, cancel, setup, and optional stop-time review flow while adding the grok:grok-rescue subagent.
Project overview
Role Sole adapter and maintainer of the Claude Code port — Grok CLI headless orchestration, command surface, grok:grok-rescue, job store, failure classification
Scenario
Claude Code needed a bounded path to ask Grok for review or rescue work without making Grok the owner of local files or git. Manual tool switching weakens scope and evidence tracking.
Product strategy
I ported the official command surface to Grok CLI headless mode, with job controls, a grok:grok-rescue subagent, stop-time review, and explicit boundaries. Claude Code keeps verification and shipping decisions.
Outcome and current stage
Public v0.2.0 · port of the official codex-plugin-cc surface · Grok CLI headless delegation · optional stop-time review gate
My contribution
- Claude Code commands for review, adversarial-review, rescue, transfer, status, result, cancel, and setup
- Integration with the Grok CLI's headless mode for bounded second-model review and rescue
- grok:grok-rescue subagent plus status/result/cancel controls for inspectable jobs
- 0.2.0 came out of auditing two months of recorded use — 41 surviving job records, 125 tool events, 40 session transcripts. Every run now announces its job id before it starts and carries a hard deadline; a run whose worker died is closed out as an orphan instead of staying 'running' forever; failures carry typed codes, with quota and auth exhaustion holding off further calls; and setup reports leftover 0.1-era job directories rather than deleting them
- Optional stop-time review gate that keeps Claude Code responsible for final verification