mcp · handle kaban
ai_omni_skills · job 73%shrimp_task_manager · job 77%kanban_mcp · job 79%doriku · job 83%sprintra · job 82%Claw Code · job 76%Relay · job 75%local_coding_agent · job 78%wormhole_mcp · job 72%CodeAgent Mobile · job 77%coding_tools_mcp · job 76%rtfm · job 74%sync · job 80%forkit · job 74%dotbot · job 79%costwise_mcp · job 72%toolkit · job 71%tasklix · job 74%retasc · job 80%Swarm MCP Server · job 82%objective · job 82%bothread · job 77%Docket · job 82%astryke_hub · job 72%easykanban · job 73%MemHub · job 78%loopertaskcom · job 73%frontier_orchestrator · job 75%ProjectBrain · job 78%board_mcp · job 77%buggazi · job 76%Kiokuko · job 73%sourcebook · job 75%kawacode_mcp · job 78%threadctx · job 72%desktop_commander_mcp · job 70%tracker · job 71%plate · job 70%morph · job 71%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series