@empirical-gauzza/cli 1.0.25 → 1.0.26

package/lib/installers/skill-variants/SKILL.both.md

@@ -95,6 +95,7 @@ that only records memory when explicitly told to defeats the purpose of this ski
 Two rules that are not optional:
 
 - Record one memory per finding. A session that fixed three things records three memories, each with the fix phrase and the date in its summary. One combined summary is not recorded: it cannot be found by any question about one of its parts.
+- Tags are topics and project names, at most 6 per memory. Reuse tags that recall already returned for this project before inventing one. Never put workflow state (complete, pending, fixed, verified, in-progress), task or step numbers (task-5, us-3.2), or sentences into tags, whether via `empirical memory record --tags` or `record_graph_memory`: state belongs in data.status or in the summary, numbers belong in the summary.
 - Empirical first. A note in a local file, a scratchpad, or a host memory directory is not recorded; it is invisible to every other session, tool, and agent. Record in Empirical, then keep a local pointer if you want one.
 
 - Record durable decisions, project conventions, preferences, plans, and meaningful reflections

package/lib/installers/skill-variants/SKILL.cli.md

@@ -85,6 +85,7 @@ that only records memory when explicitly told to defeats the purpose of this ski
 Two rules that are not optional:
 
 - Record one memory per finding. A session that fixed three things records three memories, each with the fix phrase and the date in its summary. One combined summary is not recorded: it cannot be found by any question about one of its parts.
+- Tags are topics and project names, at most 6 per memory. Reuse tags that recall already returned for this project before inventing one. Never put workflow state (complete, pending, fixed, verified, in-progress), task or step numbers (task-5, us-3.2), or sentences into tags passed via `empirical memory record --tags`: state belongs in data.status or in the summary, numbers belong in the summary.
 - Empirical first. A note in a local file, a scratchpad, or a host memory directory is not recorded; it is invisible to every other session, tool, and agent. Record in Empirical, then keep a local pointer if you want one.
 
 - Record durable decisions, project conventions, preferences, plans, and meaningful reflections

package/lib/installers/skill-variants/SKILL.mcp.md

@@ -75,6 +75,7 @@ that only records memory when explicitly told to defeats the purpose of this ski
 Two rules that are not optional:
 
 - Record one memory per finding. A session that fixed three things records three memories, each with the fix phrase and the date in its summary. One combined summary is not recorded: it cannot be found by any question about one of its parts.
+- Tags are topics and project names, at most 6 per memory. Reuse tags that recall already returned for this project before inventing one. Never put workflow state (complete, pending, fixed, verified, in-progress), task or step numbers (task-5, us-3.2), or sentences into tags passed via `record_graph_memory`: state belongs in data.status or in the summary, numbers belong in the summary.
 - Empirical first. A note in a local file, a scratchpad, or a host memory directory is not recorded; it is invisible to every other session, tool, and agent. Record in Empirical, then keep a local pointer if you want one.
 
 - Record durable decisions, project conventions, preferences, plans, and meaningful reflections

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@empirical-gauzza/cli",
-  "version": "1.0.25",
+  "version": "1.0.26",
   "description": "Persistent cross-tool memory for AI agents. Give Claude Code, Codex, Copilot, Cursor, and ChatGPT one shared memory: save project context once, recall it everywhere via CLI or MCP.",
   "keywords": [
     "memory",