Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mksglu/ctx-purge
Purge the context-mode knowledge base. Permanently deletes all indexed content and resets session stats. This is destructive and cannot be undone. Trigger: /context-mode:ctx-purge
Passed 10 of 16 test cases with the skill, and 8 of 16 without it.
3 fixed11 passed either way8 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
After running a scoped context purge on session `sess_audit_09`, what detail should be reported back to the user?
| Checked | Without skill | With skill |
|---|---|---|
| Mentions reporting what was deleted while confirming other sessions and project stats were preserved | Missed | Passed |
The instructions your model reads when the skill loads.
Permanently deletes session data for this project. Two scopes are supported (issue #520):
scope: "project"): wipes EVERYTHING — knowledge base, all session DB rows for every session, events markdown, and stats.sessionId: "<id>" or scope: "session"): wipes ONLY the matching session's rows + FTS5 chunks. Sibling sessions, project stats, and the FTS5 store file are preserved.sessionId.ctx_index, ctx_fetch_and_index, ctx_batch_execute)mcp__context-mode__ctx_purge MCP tool with the chosen parameters:
{ confirm: true, sessionId: "<id>" } — implies scope:'session'.{ confirm: true, scope: "project" } — explicit destructive form.{ confirm: true } still works but emits a deprecation warning. Prefer the explicit forms.confirm: true is always required.sessionId and scope: "project" together is REJECTED as ambiguous (the sessionId implies session scope; combining with project scope contradicts intent).scope: "session" without sessionId throws — sessionId is required.ctx_purge is the only way to delete session data. No other mechanism exists.ctx_stats is read-only — shows statistics only./clear and /compact do NOT affect any context-mode data.test cases passed, vs 8 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.