Sync Claude marketplace bridge to monorepo plugin

.claude-plugin/marketplace.json

@@ -11,8 +11,8 @@
     {
       "name": "claude-code",
       "source": "./plugins/claude-code",
-      "description": "Persistent semantic memory for Claude Code — user preferences, project context, prior decisions, and codebase facts that survive across sessions.",
-      "version": "0.1.14",
+      "description": "Persistent semantic memory for Claude Code - user preferences, project context, prior decisions, and codebase facts that survive across sessions.",
+      "version": "0.1.16",
       "category": "productivity",
       "homepage": "https://docs.atomicstrata.ai/integrations/coding-agents/claude-code",
       "license": "Apache-2.0"

plugins/claude-code/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "atomicmemory",
-  "version": "0.1.14",
+  "version": "0.1.16",
   "description": "Persistent semantic memory for Claude Code — user preferences, project context, prior decisions, and codebase facts that survive across sessions.",
   "author": {
     "name": "AtomicMemory",
@@ -11,7 +11,7 @@
   "mcpServers": {
     "atomicmemory": {
       "command": "npx",
-      "args": ["-y", "--package=@atomicmemory/mcp-server@^0.1.1", "atomicmemory-mcp"],
+      "args": ["-y", "--package=@atomicmemory/mcp-server@^0.1.2", "atomicmemory-mcp"],
       "env": {
         "ATOMICMEMORY_API_URL": "${ATOMICMEMORY_API_URL:-}",
         "ATOMICMEMORY_API_KEY": "${ATOMICMEMORY_API_KEY:-}",

plugins/claude-code/README.md

@@ -123,7 +123,7 @@ claude plugin update claude-code@atomicmemory
 claude plugin install claude-code@atomicmemory
 ```
 
-The plugin spawns `@atomicmemory/mcp-server` from the npm registry via `npx`, so no local build is needed. If you're developing the MCP server itself and want Claude Code to load a local checkout instead, override the manifest's `mcpServers.atomicmemory.command`/`args` in a private settings file rather than editing the published manifest.
+The plugin spawns `@atomicmemory/mcp-server` from the npm registry via `npx`, so no local build is needed. If you're developing the MCP server itself and want Claude Code to load a local checkout instead, override the manifest's `mcpServers.atomicmemory.command`/`args` in a local settings file rather than editing the published manifest.
 
 If `claude plugin marketplace list` shows `atomicmemory` pointing at an old checkout, replace the marketplace entry from this repo first:
 
@@ -175,7 +175,7 @@ plugins/claude-code/
 └── README.md
 ```
 
-The plugin spawns [`@atomicmemory/mcp-server`](../../packages/mcp-server) from the npm registry via `npx -y --package=@atomicmemory/mcp-server@^0.1.1 atomicmemory-mcp`, so a `claude plugin install` is self-contained — no local clone or build required. Most semantic memory operations go through the MCP tools. Latency-sensitive prompt retrieval uses `/v1/memories/search/fast` directly, and lifecycle scripts write deterministic records to `/v1/memories/ingest/quick` with `skip_extraction=true` because command hooks cannot talk to Claude Code's already-running stdio MCP child. Hook record content stays clean and human-readable; lifecycle provenance, scope, dedupe keys, session IDs, cwd, transcript paths, tool counts, and validation details are sent separately in request `metadata` and persisted to the memory's `metadata` JSONB column, with `sourceSite` / `sourceUrl` continuing to carry the provider/route identity.
+The plugin spawns [`@atomicmemory/mcp-server`](../../packages/mcp-server) from the npm registry via `npx -y --package=@atomicmemory/mcp-server@^0.1.2 atomicmemory-mcp`, so a `claude plugin install` is self-contained — no local clone or build required. Most semantic memory operations go through the MCP tools. Latency-sensitive prompt retrieval uses `/v1/memories/search/fast` directly, and lifecycle scripts write deterministic records to `/v1/memories/ingest/quick` with `skip_extraction=true` because command hooks cannot talk to Claude Code's already-running stdio MCP child. Hook record content stays clean and human-readable; lifecycle provenance, scope, dedupe keys, session IDs, cwd, transcript paths, tool counts, and validation details are sent separately in request `metadata` and persisted to the memory's `metadata` JSONB column, with `sourceSite` / `sourceUrl` continuing to carry the provider/route identity.
 
 ## Lifecycle hooks
 

plugins/claude-code/package.json

@@ -1,12 +1,12 @@
 {
   "name": "@atomicmemory/claude-code-plugin",
-  "version": "0.1.14",
+  "version": "0.1.16",
   "description": "AtomicMemory plugin for Claude Code — persistent semantic memory across sessions.",
   "private": false,
   "license": "Apache-2.0",
   "repository": {
     "type": "git",
-    "url": "git+https://github.com/atomicstrata/atomicmemory-integrations.git",
+    "url": "git+https://github.com/atomicstrata/atomicmemory.git",
     "directory": "plugins/claude-code"
   },
   "files": [
@@ -18,5 +18,9 @@
   ],
   "scripts": {
     "test": "bash scripts/__tests__/quick-ingest-body.sh && bash scripts/__tests__/load-env-defaults.sh && bash scripts/__tests__/auth-header.sh && bash scripts/__tests__/package-files.sh"
-  }
+  },
+  "bugs": {
+    "url": "https://github.com/atomicstrata/atomicmemory/issues"
+  },
+  "homepage": "https://github.com/atomicstrata/atomicmemory/tree/main/plugins/claude-code#readme"
 }

plugins/claude-code/scripts/__tests__/quick-ingest-body.sh

@@ -12,7 +12,7 @@
 #   3. real metadata object → 6-field body with `metadata` deep-
 #      equal to the input
 #   4. malformed JSON → exits non-zero with a non-empty stderr
-#      (CLAUDE.md "no fallback values")
+#      (project rule: no fallback values)
 #
 # Runs entirely in-process: no Docker, no curl, no network.
 # The companion `metadata-roundtrip.sh` script is the optional

plugins/claude-code/skills/atomicmemory/SKILL.md

@@ -32,7 +32,7 @@ Use `mode: "text"` for standalone facts. Use `mode: "messages"` only when the fu
 ## What NOT to save
 
 - Ephemeral task state (current WIP, what file you're editing)
-- Facts already documented in CLAUDE.md, README, or recent git commits
+- Facts already documented in repository docs, README files, or recent git commits
 - Anything the user can trivially re-derive from the code
 - Debugging session scratch