hmem-mcp 3.7.1 → 3.7.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "hmem-mcp",
-  "version": "3.7.1",
+  "version": "3.7.2",
   "description": "Humanlike memory for AI agents — MCP server with 5-level lazy-loaded SQLite memory",
   "author": "Bumblebiber",
   "license": "MIT",

package/skills/hmem-read/SKILL.md

@@ -19,6 +19,11 @@ Do NOT just read this document — execute a tool call immediately.
 If the tool `read_memory` is not available, tell the user:
 "read_memory tool not found. Run `hmem init` to configure the MCP server."
 
+**Announcements:** If `read_memory` or `hmem-sync pull` shows urgent announcements
+(yellow warnings at the top), act on them **immediately** before doing anything else.
+These are broadcast messages from the user or another device — typically config changes,
+server migrations, or breaking updates that must be handled first.
+
 ---
 
 ## Path A: Fresh Session Start (no context yet)
@@ -96,12 +101,12 @@ read_memory(context_for="P0029", min_tag_score=7)  # stricter — only strong ma
 ## Adapt Communication to User Skill Level
 
 After loading memory, check H-prefix entries for **User Skill Assessments** (e.g. H0010 "User Skill: IT").
-These tell you the user's expertise level per topic — adapt your language accordingly:
+These contain 1-10 scores per subtopic — adapt your language accordingly:
 
-- **Beginner**: Explain concepts, avoid jargon, use analogies
-- **Intermediate**: Brief explanations, some jargon OK
-- **Advanced**: Direct technical language, skip basics
-- **Expert**: Peer-level discussion, challenge assumptions
+- **1-4**: Explain concepts, avoid jargon, use analogies
+- **5-6**: Brief explanations, some jargon OK
+- **7-8**: Direct technical language, skip basics
+- **9-10**: Peer-level discussion, challenge assumptions
 
 If no skill assessment exists yet, create one based on the user's vocabulary and questions
 (see hmem-write skill for the H-prefix convention).

package/skills/hmem-sync-setup/SKILL.md

@@ -176,6 +176,57 @@ Add `HMEM_SYNC_PASSPHRASE` to `.mcp.json` env block and restart the AI tool.
 
 ---
 
+## Urgent Announcements
+
+Broadcast messages to all synced devices. Each device sees announcements once on the next pull.
+
+### When to send
+
+- Server migration (new URL, DNS change)
+- Breaking config changes (e.g. "update maxL1Chars to 200")
+- Security issues (compromised token, rotate credentials)
+- Coordinated action needed across all devices
+
+### How to send
+
+```bash
+# From the directory containing .hmem-sync-config.json:
+npx hmem-sync announce --message "Server URL changing to https://new-server/hmem-sync"
+
+# Or via curl:
+curl -X POST https://server/hmem-sync/announcements \
+  -H "Authorization: Bearer $TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{"message":"Your urgent message here"}'
+```
+
+### How to edit or delete
+
+```bash
+# List all announcements:
+curl -s https://server/hmem-sync/announcements -H "Authorization: Bearer $TOKEN"
+
+# Edit (by ID from list):
+curl -X PUT https://server/hmem-sync/announcements/2 \
+  -H "Authorization: Bearer $TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{"message":"Corrected message"}'
+
+# Delete:
+curl -X DELETE https://server/hmem-sync/announcements/2 \
+  -H "Authorization: Bearer $TOKEN"
+```
+
+### When you RECEIVE an announcement
+
+Announcements appear as yellow warnings before pull output. They indicate urgent action is needed.
+
+**Act on them immediately — before any other work.** Do not write to memory, do not start tasks.
+Read the message, execute the requested action (config change, URL update, etc.), verify it worked,
+then continue with normal work.
+
+---
+
 ## Troubleshooting
 
 | Problem | Cause | Fix |