Castai Pack
18 governed CAST AI operator workflows for Kubernetes cost monitoring and autoscaling
- Type
- Plugin
- Repository
- jeremylongshore/tons-of-skills-marketplace
- GitHub stars
- 2.8k
- License
- MIT
- Repo last updated
- Sep 27, 2026
- Version
- 2.0.0
- Author
- Jeremy Longshore
What Castai Pack is
Castai Pack is a plugin published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”
A plugin is a package that bundles skills, slash commands, subagents, hooks, and MCP connectors so they install together. Plugins are plain files with a manifest at .claude-plugin/plugin.json, and they work in both Claude Code and Claude Cowork.
Installing Castai Pack adds everything it ships in one step. Connectors inside a plugin still need to be connected separately, and hooks and subagents only run in Cowork and Claude Code, not in regular chat.
How to install Castai Pack
Claude Code
- Add the repository as a plugin marketplace: claude plugin marketplace add jeremylongshore/tons-of-skills-marketplace
- Install the plugin: claude plugin install castai-pack@<marketplace-name>, using the marketplace name from the repository's .claude-plugin/marketplace.json.
- Restart the session if the new skills or commands don't appear straight away.
Claude Cowork
- Open Customize → Plugins and choose Add marketplace.
- Enter jeremylongshore/tons-of-skills-marketplace (the owner/repo shorthand works for GitHub).
- Find Castai Pack in the list, click Install, then connect any connectors it needs from its Connectors tab.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
An excerpt from plugins/saas-packs/castai-pack/.claude-plugin/plugin.json, shared under the repository's MIT license. Read the full file on GitHub.
> 18 Grade-A Claude Code workflows for governed Kubernetes cost monitoring and autoscaling with CAST AI
This pack helps platform, SRE, FinOps, and security teams operate CAST AI without guessing API paths, chart topology, quota values, or savings claims. Every skill is a distinct decision or operating workflow, includes dated first-party source notes, and defaults to observation, planning, and bounded canaries before mutation.
Install
/plugin install castai-pack@claude-code-plugins-plusThe public skills can also be discovered through the official Skills CLI from jeremylongshore/tons-of-skills-marketplace.
Current Product Boundaries
- castctl is the recommended connection path for supported Kubernetes clusters.
- New connections use the unified castai umbrella Helm chart; legacy standalone releases can be consolidated with the documented migration workflow.
- Cost Monitoring is always enabled. Node Autoscaling and Workload Autoscaling are separate automation decisions.
- REST authentication uses X-API-Key and the regional US, EU, or India base. Enterprise child-organization calls also need X-CastAI-Organization-Id.
- Workload policies can control vertical recommendations and native autoscaling/v2 HPAs. HPA ownership transfer is explicit and reviewable.
- Savings reports depend on baseline, adoption, time window, and pricing assumptions. They are reconciled rather than treated as billing truth.
Skills
Onboarding and Integration
Autoscaling and Cost
Reliability and Governance
Recommended Sequence
- Use castai-reference-architecture and castai-security-basics to establish ownership and permissions.
- Use castai-install-auth, then castai-hello-world or castai-core-workflow-a for observation-first onboarding.
- Use castai-core-workflow-b for a measured automation canary.
- Use the cost, performance, CI, readiness, and upgrade skills for ongoing operations.
Source Policy
The skills cite current first-party CAST AI documentation and the live API specification. Exact versions, endpoints, policy thresholds, cloud permissions, and release commands must still be derived from the target environment and pinned repository configuration.
Links
- CAST AI documentation
- Connect with castctl
- Hosted components
- API access
- API specification
- Terraform provider
- CAST AI GitHub organization
- CAST AI status
License
MIT
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Castai Pack?
Castai Pack is a plugin for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. 18 governed CAST AI operator workflows for Kubernetes cost monitoring and autoscaling
How do I install Castai Pack in Claude Code?
Add the repository as a plugin marketplace: claude plugin marketplace add jeremylongshore/tons-of-skills-marketplace Install the plugin: claude plugin install castai-pack@<marketplace-name>, using the marketplace name from the repository's .claude-plugin/marketplace.json. Restart the session if the new skills or commands don't appear straight away.
Can I use Castai Pack in Claude Cowork?
Open Customize → Plugins and choose Add marketplace. Enter jeremylongshore/tons-of-skills-marketplace (the owner/repo shorthand works for GitHub). Find Castai Pack in the list, click Install, then connect any connectors it needs from its Connectors tab.
Is Castai Pack safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- 003 Jeremy Vertex Ai Media Master Comprehensive Google Vertex AI multimodal mastery for Jeremy - video processing (6+ hours), audio generation, image creation with Gemini 2.0/2.5 and Imagen 4. Marketing campaign automation, content generation, and media asset production. Plugin · jeremylongshore/tons-of-skills-marketplace
- 002 Jeremy Yaml Master Agent Intelligent YAML validation, generation, and transformation agent with schema inference, linting, and format conversion capabilities Plugin · jeremylongshore/tons-of-skills-marketplace
- 000 Jeremy Content Consistency Validator Universal document consistency auditor. Runs deterministic drift checks across docs, code, tests, and CI; resolves conflicts through a per-fact-class authority registry (sot-map.yaml) instead of a global ranking; LLM-judged findings are structurally separated and advisory-only. Read-only — reports discrepancies, never fixes. Invoked automatically by /release Phase 1.6. Plugin · jeremylongshore/tons-of-skills-marketplace
- 004 Jeremy Google Cloud Agent Sdk Build, evaluate, deploy, publish, and migrate Google ADK applications with Google's maintained agents-cli workflow for Agent Runtime, Cloud Run, GKE, and Gemini Enterprise. Plugin · jeremylongshore/tons-of-skills-marketplace
- Chaos Engineering Toolkit Chaos testing for resilience with failure injection, latency simulation, and system resilience validation Plugin · jeremylongshore/tons-of-skills-marketplace
- Capacity Planning Analyzer Analyze and plan for capacity requirements Plugin · jeremylongshore/tons-of-skills-marketplace
- Ci Cd Pipeline Builder Build CI/CD pipelines for GitHub Actions, GitLab CI, Jenkins, and more Plugin · jeremylongshore/tons-of-skills-marketplace
- Canva Pack 30 governed Canva Connect operator workflows for OAuth, designs, asynchronous jobs, and secure integrations Plugin · jeremylongshore/tons-of-skills-marketplace