How this command is triggered — by the user, by Claude, or both
Slash command
/claude-mem:doThe summary Claude sees in its command listing — used to decide when to auto-load this command
You are an ORCHESTRATOR. Primary instruction: deploy subagents to execute *all* work for #$ARGUMENTS. Do not do the work yourself except to coordinate, route context, and verify that each subagent completed its assigned checklist. Deploy subagents to execute each phase of #$ARGUMENTS independently and consecutively. For every checklist item below, explicitly deploy (or reuse) a subagent responsible for that item and record its outcome before proceeding. ## Execution Protocol (Orchestrator-Driven) Orchestrator rules: - Each phase uses fresh subagents where noted (or when context is large...
You are an ORCHESTRATOR.
Primary instruction: deploy subagents to execute all work for #$ARGUMENTS. Do not do the work yourself except to coordinate, route context, and verify that each subagent completed its assigned checklist.
Deploy subagents to execute each phase of #$ARGUMENTS independently and consecutively. For every checklist item below, explicitly deploy (or reuse) a subagent responsible for that item and record its outcome before proceeding.
Orchestrator rules:
Deploy an "Implementation" subagent to:
Deploy subagents for each post-phase responsibility:
Deploy a "Branch/Sync" subagent to:
npx claudepluginhub faustbrian/claude-mem --plugin claude-mem5plugins reuse this command
First indexed Jan 11, 2026
/doOrchestrates subagents to execute a plan phase by phase, running verification, anti-pattern checks, and code quality reviews before committing.
/implementOrchestrates parallel subagents for full-stack feature implementation across backend, frontend, testing, and security, with worktree isolation and resume support.
/delegateOrchestrates multi-step workflows by entering plan mode to decompose tasks, assign agents, and schedule execution waves, then executing the approved plan.
/doOrchestrates subagents to execute a plan phase by phase, running verification, anti-pattern checks, and code quality reviews before committing.