From olam
Destroy an Olam world and clean up all resources (containers, worktrees, services, R2 artifacts). Use when the user says "destroy world", "tear down", "clean up world", "kill that world", "remove environment", or wants to free resources held by a world they no longer need. Confirms current state before destroying.
How this skill is triggered — by the user, by Claude, or both
Slash command
/olam:destroy [world-id][world-id]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Destroy a world, cleaning up containers, worktrees, and services.
Destroy a world, cleaning up containers, worktrees, and services.
Parse the argument as the world ID.
If no argument, call olam_list to show available worlds and ask which to destroy.
Call olam_status to show current state before destroying (confirmation surface — operator sees what they are about to lose).
Remind the user about olam-crystallize if the world has uncaptured thoughts. Destroy is irreversible for in-memory trace state.
Call olam_destroy with the world ID.
Confirm destruction and surface any retained artifact paths (R2 snapshots persist in CF mode).
Destroy flushes the trace buffer, archives artifacts to R2, and
releases the Durable Object. Dashboards at
$OLAM_WORKER_URL/sandbox/<id>/ will return 404 once the DO is
released. R2 snapshots persist and can be inspected via the CF
dashboard if needed for post-mortem.
Reference:
docs/CF_WORLDS_SPEC.md §4.4.
olam_destroy returns "world not found" — call olam_list to verify the ID; the world may have already been destroyed.olam clean for that.npm uninstall -g @pleri/olam-cli plus removing ~/.olam/.olam-crystallize (must run before destroy if you want to keep the thought graph).olam-list — find worlds eligible for destruction.olam-status — inspect before destroying.olam-create — start a new world (after this one is gone).npx claudepluginhub pleri/olam-cliProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.