Operative Namespace
@peat_gator
2 extensions
@peat_gator/lite-forge-19
AI-assisted analysis of release notes and changelogs. Returns rubric-scored JSON suitable for downstream judging. ## Quick start Add `@peat_gator/lite-forge-19` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @peat_gator/lite-forge-19 workflows: - name: lite-forge-19-run jobs: - name: main steps: - name: run model: peat_gator/lite-forge-19 method: run ``` Run with `swamp workflow run lite-forge-19-run`. The first invocation prints what it would change; pass `--apply` to commit. ## What's inside - **Composable workflows** — wire methods into multi-step DAGs with retry, idempotency, and per-step logs. - **Drivers** — bounded concurrency, structured retries, and CloudWatch / OpenTelemetry-friendly tags. ## Configuration Configure via `~/.swamp/config.yaml` or environment variables. The full method reference and rubric format live in the package's `manual/` directory. **Labels:** `release` `diff` `python`
@peat_gator/lite-pilot-05
Pull developer tooling, normalize the shape, and stream into your downstream pipeline. Pagination is automatic. ## Quick start Add `@peat_gator/lite-pilot-05` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @peat_gator/lite-pilot-05 workflows: - name: lite-pilot-05-run jobs: - name: main steps: - name: diff model: peat_gator/lite-pilot-05 method: diff ``` Run with `swamp workflow run lite-pilot-05-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. - **Composable workflows** — wire methods into multi-step DAGs with retry, idempotency, and per-step logs. - **Reports** — markdown roll-ups grouped by label and breaking-change flag. - **Skills** — Claude Code skills with tool whitelists and trigger-phrase manifests. ## Configuration Configure via `~/.swamp/config.yaml` or environment variables. The full method reference and rubric format live in the package's `manual/` directory. **Labels:** `tooling` `ai` `yaml`