Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion plugins/code-review/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -26,11 +26,12 @@ Performs automated code review on a pull request using multiple specialized agen

**Usage:**
```bash
/code-review [--comment]
/code-review [--comment] [--model haiku|sonnet|opus]
```

**Options:**
- `--comment`: Post the review as a comment on the pull request (default: outputs to terminal only)
- `--model <value>`: Override the model used for all agents. Valid values: `haiku`, `sonnet`, `opus`. Default uses per-step model selection (Haiku for lightweight tasks, Sonnet for compliance, Opus for bug detection).

**Example workflow:**
```bash
Expand Down
2 changes: 2 additions & 0 deletions plugins/code-review/commands/code-review.md
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ Provide a code review for the given pull request.
- All tools are functional and will work without error. Do not test tools or make exploratory calls. Make sure this is clear to every subagent that is launched.
- Only call a tool if it is required to complete the task. Every tool call should have a clear purpose.

If `--model <value>` is provided in the arguments, use that model for all agents in every step below, overriding the per-step defaults. Valid values: `haiku`, `sonnet`, `opus`. If an invalid value is provided, stop and print: "unknown model — valid values are haiku, sonnet, opus". If `--model` is not provided, use the model specified per step.

To do this, follow these steps precisely:

1. Launch a haiku agent to check if any of the following are true:
Expand Down