opencode-plugin-cc — OpenCode inside Claude Code
- JavaScript
- Node.js
- Claude Code Plugin
- OpenCode CLI
- background jobs
A Claude Code port of the official openai/codex-plugin-cc surface, adapted to drive the local OpenCode CLI. It lets Claude Code hand bounded review, adversarial-review, rescue, transfer, status, result, cancel, setup, and optional stop-time review work to OpenCode, which can front Anthropic, OpenAI, Google, open-weight, and free zen models.
Project overview
Role Sole adapter and maintainer of the Claude Code port — OpenCode CLI wiring, command surface, job store, failure classification, stop-time gate
Scenario
Claude Code needed a controlled way to use a second model without leaving its local workflow or losing ownership of context. The risk was handing too much scope to another tool.
Product strategy
I ported the official command surface to OpenCode CLI and kept job control, stop-time review, and the delegation boundary explicit. Claude Code remains responsible for files, git, verification, and final judgment.
Outcome and current stage
Public v0.2.0 · port of the official codex-plugin-cc surface · multi-provider second-model delegation · optional stop-time review gate
My contribution
- Claude Code commands for review, adversarial-review, rescue, transfer, status, result, cancel, and setup
- Bounded delegation to whichever model OpenCode is configured with — OpenCode's own provider range covers Anthropic, OpenAI, Google, open-weight, and free opencode zen models
- A background job store that prints the job handle before the run starts, status/result/cancel controls, and an optional stop-time review gate
- 0.2.0 turned failure into data: a run is classified completed, incomplete, or failed instead of pass/fail; a failed run carries a typed class such as model_unauthorized or quota_exhausted; job records are reconciled against process liveness every time they are read; and structured review output is validated against a schema before it is believed