---
title: "starlight-agent-designer"
description: "Design valuable Starlight agents with constitutional foundations, architecture decisions, activation prompts, scoped contracts and verifiable evidence. Includes Foundry design workflows and an in-process guardrail refere"
canonical: https://agentpluginsdirectory.com/plugins/starlight-agent-designer
last-updated: 2026-10-11
---

# starlight-agent-designer
Design valuable Starlight agents with constitutional foundations, architecture decisions, activation prompts, scoped contracts and verifiable evidence. Includes Foundry design workflows and an in-process guardrail reference; production runtime integration is separate.
- Slug: starlight-agent-designer
- Publisher: Starlight Intelligence
- Repository: https://github.com/frankxai/Starlight-Intelligence-System
- Manifest: plugins/starlight-agent-designer/plugin.json
- Version: 0.1.0
- License: MIT
- Category (editorial): other
- Skills: 5 (agent-forge, skill-forge, starlight-agent-designer, system-forge, taste-engine)
- MCP servers: 0
- Stars: 11
- Repository created: 2025-12-18
- Repository last pushed: 2026-10-11
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/starlight-agent-designer
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- agent-forge: Design an agent only when a durable autonomy boundary is justified; compile it only when a Foundry runtime is available. Use for persistent decision rights, distinct memory, constrained tools, ownership transfer, or an ongoing schedule, channel, or API trigger.
- skill-forge: Forge a reusable, portable skill from a proven workflow or capability brief. Use when the work needs repeatable instructions, triggers, guardrails, and evidence tests but does not need a persistent autonomous identity.
- starlight-agent-designer: Design or improve Starlight agents from a value opportunity through architecture, agent contracts, prompt engineering, bounded proactivity and evaluation. Use when asked for an Agent Designer, a powerful agent architecture, constitutional guardrails, agent activation, or a frontier technology propo…
- system-forge: Design a multi-capability system as a swarm, vertical, or plugin; compile it only when a Foundry runtime is available. Use when several skills or agents need explicit topology, shared state, conflict resolution, termination, deployment adapters, and cross-surface packaging.
- taste-engine: Turn subjective quality intent into executable hard gates, weighted rubrics, exemplars, anti-exemplars, blind comparison, and independent judge evidence. Use for high-value artifacts where correctness alone is insufficient.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.