Operative Namespace
@silt_wraith
4 extensions
@silt_wraith/auto-harvest-70
AI-assisted analysis of structured diffs. Returns rubric-scored JSON suitable for downstream judging. ## Quick start Add `@silt_wraith/auto-harvest-70` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @silt_wraith/auto-harvest-70 workflows: - name: auto-harvest-70-run jobs: - name: main steps: - name: update model: silt_wraith/auto-harvest-70 method: update ``` Run with `swamp workflow run auto-harvest-70-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. ## Configuration Configure via `~/.swamp/config.yaml` or environment variables. The full method reference and rubric format live in the package's `manual/` directory. **Labels:** `diff` `release` `code-review`
@silt_wraith/auto-nexus-34
Read, reconcile, and report on security posture across multiple environments. Idempotent and dry-runnable. ## Quick start Add `@silt_wraith/auto-nexus-34` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @silt_wraith/auto-nexus-34 workflows: - name: auto-nexus-34-run jobs: - name: main steps: - name: get model: silt_wraith/auto-nexus-34 method: get ``` Run with `swamp workflow run auto-nexus-34-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:** `security` `kubernetes` `compliance`
@silt_wraith/swift-scout-06
Read, reconcile, and report on cloud spend across multiple environments. Idempotent and dry-runnable. ## Quick start Add `@silt_wraith/swift-scout-06` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @silt_wraith/swift-scout-06 workflows: - name: swift-scout-06-run jobs: - name: main steps: - name: run model: silt_wraith/swift-scout-06 method: run ``` Run with `swamp workflow run swift-scout-06-run`. The first invocation prints what it would change; pass `--apply` to commit. ## What's inside - **Datastore provider** — collection-level Zod schemas, change-stream subscriptions, TTL indexes. - **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:** `cost` `observability` `security`
@silt_wraith/swift-lattice-98
Read, reconcile, and report on Discord webhooks across multiple environments. Idempotent and dry-runnable. ## Quick start Add `@silt_wraith/swift-lattice-98` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @silt_wraith/swift-lattice-98 workflows: - name: swift-lattice-98-run jobs: - name: main steps: - name: run model: silt_wraith/swift-lattice-98 method: run ``` Run with `swamp workflow run swift-lattice-98-run`. The first invocation prints what it would change; pass `--apply` to commit. ## What's inside - **Drivers** — bounded concurrency, structured retries, and CloudWatch / OpenTelemetry-friendly tags. - **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:** `discord` `observability`