review_fanout
Launch parallel codebase-review workers, each analyzing a distinct aspect like architecture, security, or performance. Reports are saved to disk to minimize context consumption, and results can be polled and collected as a batch.
Instructions
Launch parallel codebase-review workers, one detached Antigravity (agy) job per aspect.
The code analog of research_fanout. Each worker reads the repo (via --add-dir) and reviews
ONE aspect (architecture, security, performance, tests, etc.), writes a full markdown report
to disk, and prints a short digest to stdout. Reports stay on disk so Claude's context stays
lean — poll with research_status(batch_id) and gather with collect_digests(batch_id), exactly
as for a research batch (the collectors are batch-generic).
Args:
repo_path: Absolute path to the codebase to review.
aspects: One review aspect per worker. Defaults to a 7-aspect standard sweep.
goal: Optional improvement goal to focus the review (e.g. 'prepare for multi-tenant SaaS').
tier: Model tier for every worker (default 'pro' = Gemini 3.1 Pro High).
timeout: Per-worker print-mode timeout, e.g., '10m'.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"repo_path": "<repo_path>"
},
"name": "review_fanout"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | ||
| tier | No | pro | |
| aspects | No | ||
| timeout | No | 10m | |
| repo_path | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |