Skip to main content

Operative Namespace

@keeb

keeb

5 extensions

100%Grade A

@keeb/grafana

# @keeb/grafana [Swamp](https://github.com/systeminit/swamp) extension for Grafana dashboard and alert management via the Grafana HTTP API. ## Models ### `grafana/instance` Manage dashboards, alert rules, contact points, and notification policies on a Grafana instance. | Method | Description | |--------|-------------| | `discover` | List all dashboards | | `pushDashboard` | Create or update a dashboard from a JSON file | | `exportDashboard` | Export a dashboard to JSON | | `configureContactPoint` | Configure a notification contact point (e.g. Discord webhook) | | `configureNotificationPolicy` | Set the notification routing policy | | `pushAlertRule` | Create or update an alert rule | | `createAnnotation` | Create a dashboard annotation (used to mark deploys, server events) | ## Workflows None — dashboard and alert deployment workflows are defined in the consuming project. ## Dependencies - [@keeb/ssh](https://github.com/keeb/swamp-ssh) — SSH helpers (`lib/ssh.ts`) ## Install ```bash swamp extension pull @keeb/grafana ``` ## Example Push a dashboard JSON file and create a deploy annotation: ```yaml models: - name: grafana type: "@keeb/grafana/instance" globalArguments: grafanaUrl: "http://grafana.local:3000" apiKey: "${vault.grafana.apiKey}" jobs: - name: push-and-annotate steps: - model: grafana method: pushDashboard inputs: dashboardFile: "dashboards/hosts.json" - model: grafana method: createAnnotation inputs: text: "deploy ${env.GIT_SHA}" tags: '["deploy"]' ``` ## License MIT

linux-x86_64linux-aarch64darwin-x86_64darwin-aarch64
grafanamonitoringdashboardsobservability
modelsskills
2026.04.22.3
75%Grade B

@keeb/auto-tracer-38

Inventory compliance signals, surface drift, and emit a structured report. Read-only by default; mutating ops gated behind a flag. ## Quick start Add `@keeb/auto-tracer-38` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @keeb/auto-tracer-38 workflows: - name: auto-tracer-38-run jobs: - name: main steps: - name: get model: keeb/auto-tracer-38 method: get ``` Run with `swamp workflow run auto-tracer-38-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:** `compliance` `finops` `stable`

linux-aarch64darwin-aarch64
compliancefinopsstable
modelsreports
0.0.3
91%Grade A

@keeb/rapid-pilot-48

Sync state of Claude Code skills against a desired-state YAML. Diffs are previewed before any mutation. ## Quick start Add `@keeb/rapid-pilot-48` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @keeb/rapid-pilot-48 workflows: - name: rapid-pilot-48-run jobs: - name: main steps: - name: create model: keeb/rapid-pilot-48 method: create ``` Run with `swamp workflow run rapid-pilot-48-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. - **Vault provider** — encrypted secret storage with audit trail and cross-region replication. - **Datastore provider** — collection-level Zod schemas, change-stream subscriptions, TTL indexes. - **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:** `claude-code` `evaluation`

linux-x86_64linux-aarch64darwin-x86_64darwin-aarch64
claude-codeevaluation
modelsvaultsdatastoresskills
2.0.8
58%Grade D

@keeb/core-forge-12

Read, reconcile, and report on Discord webhooks across multiple environments. Idempotent and dry-runnable. ## Quick start Add `@keeb/core-forge-12` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @keeb/core-forge-12 workflows: - name: core-forge-12-run jobs: - name: main steps: - name: diff model: keeb/core-forge-12 method: diff ``` Run with `swamp workflow run core-forge-12-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. - **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:** `discord` `metrics` `slack`

linux-aarch64darwin-aarch64darwin-x86_64
discordmetricsslack
modelsworkflowsdrivers
2.0.4
83%Grade B

@keeb/open-prism-26

Inventory AI model output, surface drift, and emit a structured report. Read-only by default; mutating ops gated behind a flag. ## Quick start Add `@keeb/open-prism-26` to your repo's `extensions` list, then reference its model in your `swamp.yaml`: ```yaml extensions: - @keeb/open-prism-26 workflows: - name: open-prism-26-run jobs: - name: main steps: - name: list model: keeb/open-prism-26 method: list ``` Run with `swamp workflow run open-prism-26-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. - **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:** `ai` `evaluation` `tooling`

darwin-x86_64darwin-aarch64linux-x86_64
aievaluationtooling
modelsworkflowsskills
1.5.6