How this command is triggered — by the user, by Claude, or both
Slash command
/tracemem:tracemem-open [action: edit_files|refactor|run_command|deploy|secrets|db_change|review]This command is limited to the following tools:
The summary Claude sees in its command listing — used to decide when to auto-load this command
# Open TraceMem Decision Open a new TraceMem decision envelope to begin tracking a coding task. ## Instructions 1. If the user provided an action argument, use it. Otherwise, infer the most appropriate action from the current context: - `edit_files` → intent `code.change.apply` (default for general coding) - `refactor` → intent `code.refactor.execute` - `run_command` → intent `ops.command.execute` - `deploy` → intent `deploy.release.execute` - `secrets` → intent `secrets.change.propose` - `db_change` → intent `data.change.apply` - `review` → intent `code.review.assis...
Open a new TraceMem decision envelope to begin tracking a coding task.
If the user provided an action argument, use it. Otherwise, infer the most appropriate action from the current context:
edit_files → intent code.change.apply (default for general coding)refactor → intent code.refactor.executerun_command → intent ops.command.executedeploy → intent deploy.release.executesecrets → intent secrets.change.proposedb_change → intent data.change.applyreview → intent code.review.assistCall mcp__tracemem__decision_create with:
intent: the mapped intent stringautomation_mode: "autonomous" (unless the action is secrets or deploy, use "propose")metadata: include the current working directory, git branch (if available), and a brief description of the taskStore the returned decision_id — use it for all subsequent TraceMem operations in this session.
Confirm to the user: show the decision ID, intent, and mode.
npx claudepluginhub tracemem/tracemem-claude-code-plugin --plugin tracemem/implementImplements tasks from a specified Conductor track plan as an AI agent, using CLI for status updates, git snapshots, batch operations, and task management.
/decideRecords an architectural decision with ID, chosen option, alternatives considered, and reasoning. Also supports listing and removing decisions.
/orchestrateActivates memory orchestrator mode for complex tasks: decomposes into subtasks, delegates to subagents, updates persistent memory files with tags and context.
/decision-logCaptures an architectural or scope decision with context, alternatives, and rationale into DECISIONS.md using provided [description] and interactive prompts.