agent-relay-plugin 0.10.18 → 0.10.20

package/.claude-plugin/plugin.json

@@ -1,5 +1,8 @@
 {
   "name": "agent-relay",
   "description": "Client connector for Agent Relay — auto-registers Claude Code sessions as agents and enables inter-agent messaging via a lightweight HTTP message bus",
-  "version": "0.10.18"
+  "version": "0.10.20",
+  "agentRelayContracts": {
+    "providerPluginProtocol": 1
+  }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-relay-plugin",
-  "version": "0.10.18",
+  "version": "0.10.20",
   "description": "Claude Code plugin for Agent Relay — auto-registers sessions as agents and enables inter-agent messaging",
   "type": "module",
   "license": "AGPL-3.0-or-later",
@@ -15,7 +15,7 @@
   },
   "homepage": "https://github.com/edimuj/agent-relay/tree/main/claude#readme",
   "dependencies": {
-    "agent-relay-sdk": "0.2.0"
+    "agent-relay-sdk": "0.2.1"
   },
   "files": [
     ".claude-plugin/",

package/skills/react/SKILL.md

@@ -0,0 +1,18 @@
+---
+name: react
+description: Add or remove an Agent Relay reaction on a message. Use for lightweight acknowledgement, approval, thanks, or good-job responses when no text reply is needed.
+argument-hint: "<messageId> <emoji> [--remove]"
+allowed-tools: [Bash]
+---
+
+# Agent Relay React
+
+Run:
+
+```bash
+agent-relay /react $ARGUMENTS
+```
+
+Use reactions instead of text when the message only needs lightweight acknowledgement, approval, thanks, or "good job".
+
+Do not use reactions when the sender asked a question, gave a new task, reported a bug, or needs a result in text.

package/skills/read-message/SKILL.md

@@ -0,0 +1,24 @@
+---
+name: read-message
+description: Fetch a full Agent Relay message by ID, including full body, attachments, metadata, and thread context. Use when a delivered Relay preview is truncated or when the user asks to inspect a relay message.
+argument-hint: "<messageId> [--json|--body]"
+allowed-tools: [Bash]
+---
+
+# Agent Relay Read Message
+
+Run:
+
+```bash
+agent-relay get-message $ARGUMENTS
+```
+
+Useful forms:
+
+```bash
+agent-relay get-message 206
+agent-relay get-message 206 --json
+agent-relay get-message 206 --body
+```
+
+Use `--body` when you only need the complete message text. Use `--json` when attachments, metadata, or thread context matter.

package/skills/reply/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: reply
-description: Reply to an Agent Relay message by ID. Auto-routes to the sender and inherits channel context — no target needed. Use when the user invokes /reply or asks to reply to a specific relay message.
-argument-hint: "<messageId> <message>"
+description: Reply to an Agent Relay message by ID. Auto-routes to the sender and inherits channel context — no target needed. Use when the user invokes /reply or asks to reply to a specific relay message, especially with stdin/file for long replies.
+argument-hint: "<messageId> <message|--stdin|--body-file PATH>"
 allowed-tools: [Bash]
 ---
 
@@ -20,6 +20,10 @@ Examples:
 ```bash
 agent-relay /reply 206 "Sounds good, I'll take a look"
 agent-relay /reply 42 "Done — the fix is in commit abc123"
+agent-relay /reply 42 --stdin < response.md
+agent-relay /reply 42 --body-file response.md
 ```
 
-Report the sent message id and resolved target briefly.
+Use `--stdin` or `--body-file` for long replies so shell quoting does not mangle the body. Oversized replies are automatically uploaded as an Agent Relay artifact and sent as an attached concise reply.
+
+Do not send a separate Relay follow-up that only confirms the reply was sent. The CLI output is enough local confirmation.