KadenMc

KadenMc/work-buddy

Command Claude Code

Load directions via mcpwork-buddywbrun("agentdocs", {"path": "tasks/task-read-directions", "depth": "full"}), then call taskread with $ARGUMENTS.

KadenMc/work-buddy

Command Claude Code

Load directions via mcpwork-buddywbrun("agentdocs", {"path": "tasks/weekly-review-directions", "depth": "full"}), then run the workflow.

KadenMc/work-buddy

Command Claude Code

Load directions via mcpwork-buddywbrun("agentdocs", {"path": "tasks/task-scattered-directions", "depth": "full"}), then call taskscattered.

KadenMc/work-buddy

Command Claude Code

Load directions via mcpwork-buddywbrun("agentdocs", {"path": "tasks/task-search-directions", "depth": "full"}), then call contextsearch with source="tasknote" and $ARGUMENTS as the query.

KadenMc/work-buddy

Command Claude Code

Load directions via mcpwork-buddywbrun("agentdocs", {"path": "tasks/triage-directions", "depth": "full"}), then run the workflow.

KadenMc/work-buddy

Command Claude Code

Load directions via mcpwork-buddywbrun("agentdocs", {"path": "vault/recon-directions", "depth": "full"}), then read .data/vaultrecon/latest.json (or run mcpwork-buddywbrun("vaultrecon") if missing/stale). Read-only — do NOT run vaultreconcollect here. Present 3–5 striking findings in plain English; no proposals…

KadenMc/work-buddy

Command Claude Code

Load directions via mcpwork-buddywbrun("agentdocs", {"path": "architecture/wb-workflow-cancel-directions", "depth": "full"}), then call the capability.

KadenMc/work-buddy

MCP server Claude CodeCodexCursor +2

MCP server "work-buddy", hosted remotely at localhost, as configured in KadenMc/work-buddy.

KadenMc/work-buddy

Instructions file

Claude Code instructions for KadenMc/work-buddy, covering work buddy, mcp gateway, capability vs workflow, workflow consent (composable) and session init (mandatory).