Agent Architect
Use when converting a product idea, workflow, or rough requirement into a concrete AI agent architecture with purpose, scope, loop, tools, memory, permissions, and success criteria.
Install
$ agentstack add skill-kingoo123-agent-harness-skills-agent-architect ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Agent Architect
Goal
Turn an idea into an implementable agent architecture.
Workflow
- Restate the agent's target user and main job.
- Define what the agent can and cannot do.
- Write the execution loop.
- Identify required tools.
- Define context and memory.
- Define safety boundaries.
- Define measurable success criteria.
- Produce a final agent spec.
Output
# Agent Architecture
## Target User
## Core Job
## Non-goals
## Loop
## Required Tools
## Context Inputs
## Memory Rules
## Permission Boundaries
## Verification
## Success Criteria
## First MVP
## Future ExtensionsSource & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kingoo123
- Source: kingoo123/agent-harness-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.