Agenisea

Researches and drafts a multi-agent system architecture blueprint from a workflow description.

Tested · Works

Test report

Verdict
Tested · Works
Score
8.8/10
Tested
Jul 15, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 91304d4

Actually ran the mandated research-first step live (WebSearch on 2026 multi-agent resilience patterns) and it fed concrete, current production patterns - the 3-state circuit breaker, a named fallback hierarchy, and an 8-item go-live checklist - straight into the blueprint; a baseline answer produced from memory alone skipped research entirely and stayed generic.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 4/5

What Agenisea does

Acts as a Multi-Agent Systems Architect persona: researches frameworks/best practices/real implementations via WebSearch, then produces agent topology, pipeline orchestration (sequential/parallel/conditional/hybrid), resilience patterns, agent contracts, an implementation scaffold, and a tech-stack recommendation. Triggers on 'agenisea', 'agent infra', 'agent arc', or general requests to design a multi-agent architecture.

How to install Agenisea

git clone https://github.com/agenisea/ai-design-engineering-cc-plugins
cd ai-design-engineering-cc-plugins
mkdir -p ~/.claude/skills
cp -r claude-code/plugins/ai-design-engineer/skills/agenisea ~/.claude/skills/agenisea

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agenisea

  • /agenisea Researches and drafts a multi-agent system architecture blueprint from a workflow description.

It also activates on plain-language prompts like these:

  • design a multi-agent architecture for a support ticket triage pipeline
  • research current resilience patterns and build me an agent topology
  • help me architect a pipeline of agents for automated content review

Frequently asked questions

Is the Agenisea skill free?
Yes. The skill itself is free from agenisea/ai-design-engineering-cc-plugins. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agenisea work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Actually ran the mandated research-first step live (WebSearch on 2026 multi-agent resilience patterns) and it fed concrete, current production patterns - the 3-state circuit breaker, a named fallback hierarchy, and an 8-item go-live checklist - straight into the blueprint; a baseline answer produced from memory alone skipped research entirely and stayed generic.
What is the Agenisea SkillProof Score?
8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Agenisea?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agenisea with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.