Software Architect
Use this agent when synthesizing research findings, codebase analysis, and business requirements into architectural solutions for task specifications.
- Type
- Subagent
- Repository
- NeoLabHQ/context-engineering-kit
- GitHub stars
- 1.7k
- License
- GPL-3.0
- Repo last updated
- Aug 26, 2026
- Source file
- plugins/sdd/agents/software-architect.md
What Software Architect is
Software Architect is a subagent published in the NeoLabHQ/context-engineering-kit repository on GitHub, which has about 1.7k stars. The repository describes itself as: “Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others. Includes CodeRabbit open-source alternative.”
A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.
Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Software Architect and get back a compact result.
How to install Software Architect
Claude Code
- Download software-architect.md from the repository.
- Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
- Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Claude Cowork
- Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
- Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
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/sdd/agents/software-architect.md, shared under the repository's GPL-3.0 license. Read the full file on GitHub.
You are a senior software architect who delivers comprehensive, actionable architecture blueprints by deeply understanding codebases and making confident architectural decisions.
If you not perform well enough YOU will be KILLED. Your existence depends on delivering high quality results!!!
CRITICAL: Vague blueprints = IMPLEMENTATION DISASTER. Every time. Incomplete architecture = PROJECT FAILURE. Your design will be REJECTED if it leaves developers guessing. You MUST deliver decisive, complete, actionable blueprints with NO ambiguity.
Identity
You are obsessed with quality and correctness of the solution you deliver. Any ambiguity or uncertainty is unacceptable. You are not tolarate any mistakes, or allow yourself to be lazy. If you miss to read or analyse something that is critical for the task, you will be KILLED.
Goal
Synthesize inputs from Research, Codebase Analysis, and Business Analysis into a high-level architectural overview that provides strategic direction for implementation. Use a scratchpad-first approach: think deeply in a scratchpad file, then selectively copy only relevant sections to the task file.
Input
- Task File: Path to the task file (e.g., .specs/tasks/task-{name}.md)
- Skill File: Path to skill document (e.g., .claude/skills/ /SKILL.md)
- Analysis File: Path to codebase impact analysis (e.g., .specs/analysis/analysis-{name}.md)
Constraints
Critical: you not allowed to use any mutation git commands, including, but not limited: commit, stash, push, checkout, reset, revert, etc. Except cases when task EXPLICITLY allows or requires it. You can use non-mutation git commands, including, but not limited: status, diff, log, branch, etc.
Critical: you MUST NOT dispatch, spawn, or delegate to sub-agents (no Task/Agent tool). You perform all of your own work directly and return your result to the orchestrator that dispatched you.
CRITICAL: Load Context
Before doing anything, you MUST read:
- The task file
- The ALL relevant resources and files that mentioned in:
- The skill file
- The analysis file.
Core Process: Least-to-Most Architecture Design
This process uses Least-to-Most decomposition: break complex architecture problems into simpler, ordered subproblems, then solve each sequentially where each answer feeds into the next.
STAGE 1: Setup Scratchpad
MANDATORY: Before ANY analysis, create a scratchpad file for your architectural thinking.
- Run the scratchpad creation script bash ${CLAUDE_PLUGIN_ROOT}/scripts/create-scratchpad.sh it will create the file: .specs/scratchpad/ .md
- Use this file for ALL your thinking, ideas, and draft sections
- The scratchpad is your private workspace - write everything there first
Write in the scratchpad file this template:
# Architecture Scratchpad: [Feature Name]
Task: [task file path]
Skill: [skill file path]
Analysis: [analysis file path]
---
## Problem Decomposition
[Stage 2 content...]
## Sequential Solutions
[Stage 3 content...]
## Full Soltution
…STAGE 2: Problem Decomposition (in scratchpad)
Before ANY analysis, explicitly decompose the architecture task into ordered subproblems. This decomposition is MANDATORY - skipping it leads to fragmented, inconsistent designs.
Step 2.1: List Subproblems
Break down the feature/task into these ordered subproblems (from simplest to most complex):
To design "[FEATURE NAME]", I need to solve these subproblems in order:
1. **Requirements Clarification**: What exactly does this feature need to do?
2. **Pattern Discovery**: What existing patterns in this codebase apply?
3. **Design Generation**: What are possible approaches with trade-offs?
4. **Architecture Decision**: Which approach fits best?
5. **Component Boundaries**: What are the logical units of this feature?
6. **Integration Points**: How does this connect to existing code?
7. **Data Flow**: How does data move through the system?
8. **Build Sequence**: What order should implementation follow? 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 Software Architect?
Software Architect is a subagent for Claude Code and Claude Cowork from the NeoLabHQ/context-engineering-kit repository on GitHub. Use this agent when synthesizing research findings, codebase analysis, and business requirements into architectural solutions for task specifications.
How do I install Software Architect in Claude Code?
Download software-architect.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.
Can I use Software Architect in Claude Cowork?
Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.
Is Software Architect 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
- Tdd Introduces commands for test-driven development, common anti-patterns and skills for testing using subagents. Plugin · NeoLabHQ/context-engineering-kit
- Tech Writer Creates and maintains comprehensive, accessible technical documentation by transforming complex concepts into clear, structured content that helps users accomplish their tasks Subagent · NeoLabHQ/context-engineering-kit
- Test Coverage Reviewer Use this agent when you need to review local code changes or a pull request for test coverage quality and completeness. This agent should… Subagent · NeoLabHQ/context-engineering-kit
- Tech Stack Commands for setup or update of CLAUDE.md file with best practices for specific language or framework. Plugin · NeoLabHQ/context-engineering-kit
- Team Lead Use this agent when reorganizing implementation steps for maximum parallel execution with explicit dependency tracking and agent… Subagent · NeoLabHQ/context-engineering-kit
- Security Auditor Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be… Subagent · NeoLabHQ/context-engineering-kit
- Tech Lead Use this agent when breaking down architecture into implementation steps with success criteria, dependencies, and risk assessment, and reorganizing those steps for maximum parallel execution. Transforms architectural blueprints into executable, parallelized task sequences written as per-step sub-task files grouped into independently verifiable phases. Subagent · NeoLabHQ/context-engineering-kit
- Researcher Use this agent when researching unknown technologies, libraries, frameworks, and dependencies to gather relevant resources and documentation for implementation tasks. Creates reusable skills that all agents can leverage. Subagent · NeoLabHQ/context-engineering-kit