Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
Build a show across lights (grandMA3), media (Resolume) and generative visuals (TouchDesigner) from one cue list, offline first. A lane whose console or app is not running is skipped and logged while the others continue; the live rig is touched only after GO. Use for "build the show", "cue list to grandMA3 Resolume and TouchDesigner", "show programming".
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
What you get: a cue sheet and a show built per lane, rehearsed offline first, with the live rig touched only after your GO. A lane that is not available is skipped, not faked.
tracker.csv, brief.md)grandma3_ping on bdb_grandma3_mcp; resolume_ping on bdb_resolume_mcp; get_td_info on bdb_td_minddesigner (pass: connected: true). MCP tools may be deferred in the harness: try to load the tool once via the harness tool search before declaring it missing. Tool not loaded, call errors or the pass condition fails → log "Missing MCP: <server> (<tool> unavailable). Start <the grandMA3 console or onPC|Resolume Arena|TouchDesigner> and check mcpServers.<server> in your harness config." and mark that lane off; the other lanes continue and every step below runs only for lanes marked on. All three off → stop and write nothing except the run log — each lane marked on or off in the run logcue-sheet.md, one row per cue with its target per lane (MA3 macro, Resolume clip, TD cue; lane off where a lane is missing) — stops for approvalcompose_cue_list and create_safety_blackout_chain, then get_td_node_errors — errors empty; offline: nothing is sent to live outputsget_composition compared with the clips the cue sheet names — every Resolume clip in the sheet is present in the composition, missing ones listed for the human to load (no MCP tool loads media)patch_fixture for each fixture in fixture_list (patching only, no macro is executed here), the full fixture list named in the WAITING FOR GO line. The run stops here until the human types GO. This changes the live console, and no hook guards it, so this GO is the only guard. One GO = this one list, one time.trigger_clip and clear_layer (Resolume), the TD cue list and execute_macro for each macro in cue-sheet.md (grandMA3), only for lanes marked on; the cue count, the macro list and the lanes named in the WAITING FOR GO line. The run stops here until the human types GO. Light, video and projection go live, and no hook guards it, so this GO is the only guard. One GO = one rehearsal pass.cue-sheet.md maps to a TD cue, Resolume clip or MA3 macro or is marked lane off; get_td_node_errors empty again after the rehearsal — mapping table and result in the run logRun log: production_artifacts/pb-show-build-<date>.md in the start directory, never committed
Rules
N. done|skipped|failed — artifact — check result) and WAITING FOR GO: <step> at each gate. A lane marked off is logged skipped with its Missing MCP line.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
The English summary is being prepared. Showing the original description.
Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.