Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use the local MCP gateway and the per-app MCP picks. Use when the human asks to check, start, enable or disable the gateway, adopt other MCP servers behind it, wonder why an MCP server is direct or shared, or hit an After Effects MCP that will not start (Node >= 24).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
The gateway is a local token-checking forwarder (127.0.0.1:7790) in front of @1mcp/agent (127.0.0.1:7791). Harness MCP files get one aos entry instead of many servers. Full reference (repo, not installed): https://github.com/hybridlabor-api/aos/blob/main/docs/mcp-gateway.md.
aos-gateway serve | start | stop | restart | status [--json] | enable | direct | adopt [--dry-run] [--json]
aos-gateway status (exit 0 only when running). Upstream health is the state of 1mcp as a whole, not per server.aos-gateway enable points the harness MCP files at the gateway. Direct: aos-gateway direct reverses it and restores removed entries.schtasks) is UNVERIFIED in the code. Elsewhere run aos-gateway serve.~/.agents/gateway/. token must be mode 600. Never print or copy its content.aos-gateway adopt --dry-run first and show the result.aos-gateway adopt only after the human agrees. It edits harness MCP files.aos-gateway restart afterwards.Adopt skips remote (url/http/sse) entries, disabled ones, names the AOS install owns, names over 26 chars, entries with inline secrets and conflicting definitions. Secrets are never copied.
github, open_design_mcp, bdb_resolume_mcp, bdb_grandma3_mcp, bdb_blender_mcp, bdb_davinci_mcp, adobe_uxp_mcp, bdb_unreal_mcp, bdb_after_effects_mcp.deja, memb_mcp, mcsc, openwiki, bdb_td_minddesigner, the official picks). A shipped entry with shared: false also stays direct.lib/gateway/config.js.bdb_after_effects_mcp needs Node >= 24. aos-gateway serve warns on an older Node and the AE upstream will not start. Fix the Node version, then restart the gateway.
mcp_picks.json keeps the first satisfied candidate per app and removes the others.
bdb_blender_official_mcp when Blender >= 5.1 is found, else bdb_blender_mcp.bdb_resolume_official_mcp when the Arena mcp/resolume_arena_mcp_server binary is found, else bdb_resolume_mcp.bdb_after_effects_mcp_legacy only with AOS_AE_MCP=legacy, else bdb_after_effects_mcp.~/.agents/gateway/ files by hand. Use the commands above.아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.