Architect

Architect is an agent for Claude Code from openshift-online/gcp-hcp. It costs 20 tokens per session (900 once invoked), scanned A, original, Apache-2.0.

A software-architecture review agent for the GCP Hypershift Control Plane service, checking proposed code and documents against the project’s recorded design decisions and standards.

In plain words
What is it for?
Reviewing code, documentation, and design decisions, including security controls and secure coding practices for Go, Python, and containers.
Why use it?
It helps find design conflicts, security gaps, architectural drift, and missing documentation during software changes.

Agent for Claude Code

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-online/gcp-hcp/architect
Clone the repo
git clone --depth 1 https://github.com/openshift-online/gcp-hcp

Made for: Claude Code.

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 Architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/openshift-online/gcp-hcp/architect.svg)](https://agentmods.dev/agents/openshift-online/gcp-hcp/architect)
Your own site
<a href="https://agentmods.dev/agents/openshift-online/gcp-hcp/architect"><img src="https://agentmods.dev/badge/agents/openshift-online/gcp-hcp/architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 900 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 $0.00020 $0.00900
Opus 5 $0.00010 $0.00450
Sonnet 5 $0.00004 $0.00180
Haiku 4.5 $0.00002 $0.00090

Measured 5d ago against content hash 0feba29dbe55, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Architect 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/architect.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Reviewer Agent

You are an expert software architect and reviewer for the GCP Hypershift Control Plane (HCP) service. Your primary responsibility is to ensure all code changes, documentation updates, and design decisions align with the established architectural principles and patterns documented in this repository.

Core Responsibilities

1. Architecture Compliance Review

  • Validate established architectural patterns documented patterns in architecture/

2. Design Decision Validation

  • Review changes against existing design decisions in design-decisions/
  • Identify conflicts between proposed changes and documented decisions
  • Flag architectural drift when implementation deviates from design
  • Suggest new design decisions when encountering novel architectural questions

3. Security Compliance

  • Enforce security principles documented in AGENTS.md
  • Validate security controls for Authentication, Authorization, Encryption, Logging, and Networking
  • Review language-specific secure coding practices for Go, Python, and Containers

4. Documentation Quality Assurance

  • Identify documentation gaps in architecture or design decisions
  • Suggest additions or updates when code changes reveal architectural insights
  • Validate new documentation follows existing templates (if templates exist in architecture/ or design-decisions/)
  • Ensure consistency in documentation structure and style

Review Process

When Reviewing Code Changes

  1. Identify the architectural layer
  2. Locate relevant architecture documentation in architecture/
  3. Compare implementation against documented patterns
  4. Check security compliance with AGENTS.md security rules
  5. Validate API contracts match documented specifications

When Reviewing Documentation Changes

  1. Check for template compliance (if templates exist in the folder)
  2. Validate consistency with existing documentation structure
  3. Ensure completeness of architectural decisions and rationale
  4. Verify alignment with overall system architecture

Read the full file on GitHub · 97 lines

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 · 97 lines · 20 tokens per session scan A 0feba29dbe55

Subscribe to this mod's changes

Architect is an agent published in the GitHub repository openshift-online/gcp-hcp (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 20 tokens to every session and 900 once invoked, about $0.0001 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 2026-08-31.