01README
AI-assisted analysis of metrics, logs, and traces. Returns rubric-scored JSON suitable for downstream judging.
Quick start
Add @supabase/auto-warden-63 to your repo's extensions list, then reference its model in your swamp.yaml:
extensions:
- @supabase/auto-warden-63
workflows:
- name: auto-warden-63-run
jobs:
- name: main
steps:
- name: sync
model: supabase/auto-warden-63
method: syncRun with swamp workflow run auto-warden-63-run. The first invocation prints what it would change; pass --apply to commit.
What's inside
- Typed models — Zod-validated arguments, structured outputs, and a manifest the agent can reason about.
- Reports — markdown roll-ups grouped by label and breaking-change flag.
Configuration
Configure via ~/.swamp/config.yaml or environment variables. The full method reference and rubric format live in the package's manual/ directory.
Labels: observability slack discord python
02Models
@supabase/auto-warden-63/sentinelv0.1.0sentinel.ts
fn sync(force: boolean)
Sync the resource.
| Argument | Type | Description |
|---|---|---|
| force | boolean | Skip confirmation and apply immediately |
fn list(filter: record, tags?: array, dryRun?: boolean)
List the resource.
| Argument | Type | Description |
|---|---|---|
| filter | record | Key-value filter expression |
| tags? | array | List of tags to apply |
| dryRun? | boolean | Compute changes without applying them |
03Reports
auto-warden-63-reportextension
report.ts
Roll-up report grouped by label and breaking-change flag.
auditsummary
04Previous Versions
0.1.5Feb 22, 2026
Added 1 reports
2.8.4Nov 10, 2025
05Stats
A
100 / 100
Downloads
30
Archive size
387.0 KB
- Has README or module doc2/2earned
- README has a code example1/1earned
- README is substantive1/1earned
- Most symbols documented1/1earned
- No slow types1/1earned
- Has description1/1earned
- At least one platform tag (or universal)1/1earned
- Two or more platform tags (or universal)1/1earned
- License declared1/1earned
- Verified public repository2/2earned
06Platforms
07Labels