agent-designer · borghei — Claude Code skill: what it does, how to install
agent-designer — a skill for Claude Code and related platforms that plans multi-agent architectures. It generates tool definitions for Anthropic and OpenAI, diagrams communication flows, and parses runtime logs.
LicenseRef-MIT-Commons-Clause 161 installs ★ 1,183 updated 2026-11-08
npx skills add borghei/Claude-Skills --skill agent-designer -a claude-codeWhat agent-designer does
The toolkit includes three Python scripts: agent_planner.py, tool_schema_generator.py, and agent_evaluator.py. The planner evaluates requirements to choose topologies like supervisor, pipeline, swarm, or hierarchical setups, providing a Mermaid diagram alongside agent assignments.
The schema utility transforms tool specs into interfaces for OpenAI function calling and Anthropic formats, enforcing parameter types and validation rules. To inspect operational behavior, agent_evaluator.py parses execution history. It highlights task success, latency distributions, and total expenses based on the logged cost_usd property without depending on external pricing tables.
Writing outputs to files requires the -o PREFIX option, as scripts print summaries straight to stdout by default. Any unreadable or malformed JSON input terminates processing with exit code 2.
What it helps with
- select an orchestration topology for autonomous agent workflows
- produce validated tool schemas for OpenAI and Anthropic models
- render agent interaction flows into Mermaid diagrams
- diagnose bottlenecks and execution failures from agent log files
Example prompts for the agent
- Design a multi-agent supervisor architecture based on the specifications in
requirements.json. - Generate validated Anthropic and OpenAI tool schemas from
tool_specs.json. - Evaluate agent execution performance and bottleneck areas using
execution_logs.json.
How to install agent-designer
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill agent-designer -a claude-code2Manually: put the files in place
~/.claude/skills/agent-designer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agent-designer/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill agent-designer -a codex2Manually: put the files in place
.agents/skills/agent-designer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill agent-designer -a cursor2Manually: put the files in place
.cursor/skills/agent-designer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install borghei/Claude-Skills engineering/agent-designer/SKILL.md2Manually: put the files in place
.github/skills/agent-designer/SKILL.md1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill agent-designer -a gemini-cli2Platform CLI
gemini skills install https://github.com/borghei/Claude-Skills --path engineering/agent-designerManually: put the files in place
.devin/skills/agent-designer/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill agent-designer -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about agent-designer
How to install agent-designer in Claude Code?
Run npx skills add borghei/Claude-Skills --skill agent-designer -a claude-code.
What does agent-designer do?
It guides the design of multi-agent systems, formats function schemas for major model providers, and assesses execution logs for latency and cost bottlenecks.
How does agent_evaluator.py calculate model expenses?
The script does not store pricing rates. It reads financial numbers directly from the cost_usd entry inside the input log records.
Similar skills
All skills for Agent setup: memory, context, orchestration →agent-designer by other authors comes first.