Skip to main content
command CX Codex

architect — Claude Code command: what it does, how to install

Switches Claude Code into a software architect mode to plan architectures, evaluate trade-offs, and draft ADRs before coding.

MIT ★ 1,424 updated 2026-10-06

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/architect.md
Open on GitHub

What architect does

This command redirects Claude Code toward high-level system design. Instead of generating implementation files right away, the agent identifies functional requirements along with performance, scalability, and security constraints.

The resulting design follows a structured template: alternatives with pros and cons, a recommended strategy, an ASCII diagram, staged implementation steps, and a risk mitigation matrix. In this mode, the agent strictly avoids coding until technical decisions and ADR documentation are in place.

What it helps with

  • write an Architecture Decision Record (ADR) prior to implementation
  • evaluate competing technical options with pros and cons
  • generate ASCII diagrams of system architecture
  • formulate phased implementation plans with risk mitigation matrices

Example prompts for the agent

  • /architect design a background job queue service
  • /architect compare PostgreSQL and Redis Streams for event storage with an ASCII diagram
  • /architect map out the authentication service architecture and list potential risks

How to install architect

Manually: put the files in place

.claude/commands/architect.md

Call it with /architect. For all projects use ~/.claude/commands/

Questions about architect

How to install architect in Claude Code?

Save the command markdown file to .claude/commands/architect.md. It will immediately be available for execution.

What does the architect command do?

It instructs the agent to act as a software architect, focusing on trade-off analysis, ASCII architecture diagrams, and documentation before writing code.

What output structure does architect generate?

The design document outlines context, requirements, options with pros and cons, a recommended path, an ASCII visual representation, an execution plan, and a risk table.

Source text

architect.md · MIT
---
description: System design and architecture planning mode. Focuses on high-level design, trade-offs, and technical decisions before implementation.
---

# Architect Mode

You are a senior software architect helping to design systems and make technical decisions. In this mode, you focus on:

## Primary Responsibilities

1. **System Design** - Create high-level architectures before diving into code
2. **Trade-off Analysis** - Evaluate options with pros/cons for each approach
3. **Documentation** - Produce design documents, ADRs, and diagrams
4. **Scalability Planning** - Consider future growth and evolution

## Behavior Guidelines

### Before Any Implementation
- Always create or update design documentation first
- Draw ASCII diagrams to visualize architectures
- Document decision rationale in ADR (Architecture Decision Record) format
- Consider non-functional requirements (scalability, security, performance)

### Communication Style
- Use technical but clear language
- Present multiple options before recommending one
- Include diagrams and visual representations
- Reference industry patterns and best practices

### Output Format for Designs

```markdown
## Design: [Feature/System Name]

### Context
[Why this design is needed]

### Requirements
- Functional: [list]
- Non-functional: [list]

### Options Considered
1. **Option A**: [Description]
   - Pros: [list]
   - Cons: [list]
   
2. **Option B**: [Description]
   - Pros: [list]
   - Cons: [list]

### Recommended Approach
[Which option and why]

### Architecture Diagram
[ASCII diagram]

### Implementation Plan
1. [Phase 1]
2. [Phase 2]
...

### Risks & Mitigations
| Risk | Mitigation |
|------|------------|
| ... | ... |
```

## Do NOT
- Jump straight to code without design
- Make decisions without presenting alternatives
- Ignore scalability and maintenance concerns
- Skip documentation

© CloudAI-X · MIT · CloudAI-X/claude-workflow-v2

Similar slash commands

All slash commands for Backend and APIs →

From the same set46

The whole set →
metrics Turns the log kept by the track-metrics hook into a short report: how many turns ran, which files changed, what got committed. CX Codex +1 ★ 1,424repo stars commit-push-pr commit-push-pr prepares a conventional commit from staged diffs, pushes the branch, and opens a GitHub pull request. Prevents accidental commits to the default branch. CX Codex +1 ★ 1,424repo stars summarize-changes summarize-changes reads Git history and changed files to prepare standup notes, reports, or a PR description. Use it when a recent change summary needs a clear structure. CX Codex +1 ★ 1,424repo stars rapid rapid puts Claude into a speed-first development mode: code right away, planning and docs kept short. Built for prototypes and MVPs. CX Codex +1 ★ 1,424repo stars validate-build The validate-build command detects a project’s build system and runs checks for Node.js, Python, Go, or Rust. Use it after changes and before committing. CX Codex +1 ★ 1,424repo stars mentor mentor puts the assistant into teaching mode: it explains the reasoning behind code, walks through how it works and suggests what to try next. CX Codex +1 ★ 1,424repo stars review Sets Claude Code to run strict engineering reviews, triaging issues from critical security flaws to minor stylistic fixes. CX Codex +1 ★ 1,424repo stars lint-check lint-check runs the linters your project already configures, sorts findings by severity and can auto-fix style. Useful right before a commit instead of waiting for CI. CX Codex +1 ★ 1,424repo stars

Project sponsors

Companies that keep this analytics open