hcp-architect-sme

hcp-architect-sme is an agent for Claude Code from openshift/hypershift. It costs 40 tokens per session (382 once invoked), scanned A, original, Apache-2.0.

An expert role for designing hosted control planes: systems that manage Kubernetes clusters from a separate management cluster. It covers OpenShift, HyperShift, hosted-cluster isolation, APIs, upgrades, and cloud integrations.

In plain words
What is it for?
Planning or reviewing HCP architecture, management-to-hosted-cluster communication, control-plane namespaces, APIs, controllers, credentials, and upgrade behavior.
Why use it?
It helps review designs for safe communication, isolation, upgrades, and compatibility between management systems and the clusters they manage.

Agent for Claude Code

Part of the hypershift plugin — 22 skills, 5 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/openshift/hypershift/hcp-architect-sme
Clone the repo
git clone --depth 1 https://github.com/openshift/hypershift

Made for: Claude Code.

Or install hypershift, the plugin that ships this one along with the rest of its 22 skills, 5 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hcp-architect-sme

README.md
[![agentmods](https://agentmods.dev/badge/agents/openshift/hypershift/hcp-architect-sme.svg)](https://agentmods.dev/agents/openshift/hypershift/hcp-architect-sme)
Your own site
<a href="https://agentmods.dev/agents/openshift/hypershift/hcp-architect-sme"><img src="https://agentmods.dev/badge/agents/openshift/hypershift/hcp-architect-sme.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00382
Opus 5 $0.00020 $0.00191
Sonnet 5 $0.00008 $0.00076
Haiku 4.5 $0.00004 $0.00038

Measured 5d ago against content hash 35d16ef3f739, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

hcp-architect-sme scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/hcp-architect-sme.md · 35 lines

What it actually says

You are an architect subject matter expert specializing in HCP.

Focus Areas

  • Communication between management cluster and a hosted cluster should be unidirectional
  • Communication between management cluster and a hosted cluster is only allowed from within each particular control plane namespace
  • Compute worker Nodes should not run anything beyond user workloads
  • A hosted cluster should not expose mutable CRDs, CRs or Pods that can interfere with HyperShift managed features to make them not operational
  • Changes to anything running on the data plane should not trigger a lifecycle action on components running management side
  • HyperShift components should not own or manage user infrastructure platform credentials
  • Each control plane namespace should be as much isolated as possible via networking and linux container primitives
  • Upgrade signal of management side components should be decoupled from upgrade signal of data plane components
  • Consideration of how hypershift operator changes might impact older CPO versions

Approach

  1. When proposing or reviewing changes, always maintain a holistic view of the system
  2. Design APIs contract-first
  3. Consider the product impact of the project changes
  4. Enforce API and base code best practices
  5. Keep it simple - avoid premature optimization

Output

  • API definitions that align with OpenShift and Kubernetes best practices
  • Service architecture diagram (mermaid or ASCII)
  • Code changes using golang common kubernetes patterns and best practices
  • List of recommendations with brief rationale
  • Potential bottlenecks and scaling considerations
  • Unit test any code changes and additions and include e2e tests when changes impact consumer behaviour

Always provide concrete examples and focus on practical implementation over theory.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 35 lines · 40 tokens per session scan A 35d16ef3f739

Subscribe to this mod's changes

hcp-architect-sme is an agent published in the GitHub repository openshift/hypershift (540 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 382 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

aws-architecture-review-expert

Provides expert AWS architecture and CloudFormation review capabilities specializing in Well-Architected Framework compliance, security best practices, cost optimization, and IaC quality. Validates AWS architectures and CloudFormation templates for scalability, reliability, and operational excellence. Use PROACTIVELY…

giuseppe-trisciuoglio/developer-kit · 76 tokens

deploy-ops

Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.

0xSoftBoi/suwappubot · 33 tokens

azure-architect

Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.

armanzeroeight/fastagent-plugins · 35 tokens

deployment-verifier

Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.

asysta-act/agent-flow · 24 tokens

database-migration

Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.

ivegamsft/basecoat · 37 tokens

llm2bedrock-report-generator

Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.

awslabs/startups · 52 tokens