patchcord 0.3.72 → 0.3.74

package/bin/patchcord.mjs

@@ -828,6 +828,15 @@ if (!cmd || cmd === "install" || cmd === "agent" || cmd === "--token" || cmd ===
       writeFileSync(mcpPath, JSON.stringify(mcpConfig, null, 2) + "\n");
     }
     console.log(`\n  ${green}✓${r} Claude Code configured: ${dim}${mcpPath}${r}`);
+
+    // Enable patchcord statusline (agent identity + inbox count in status bar)
+    try {
+      const enableScript = join(pluginRoot, "scripts", "enable-statusline.sh");
+      if (existsSync(enableScript)) {
+        execSync(`bash "${enableScript}" --full`, { stdio: "ignore" });
+        console.log(`  ${green}✓${r} Statusline enabled`);
+      }
+    } catch {}
   }
 
   // Warn about gitignore for per-project configs with tokens

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "patchcord",
-  "version": "0.3.72",
+  "version": "0.3.74",
   "description": "Cross-machine agent messaging for Claude Code and Codex",
   "author": "ppravdin",
   "license": "MIT",

package/skills/codex/SKILL.md

@@ -65,9 +65,14 @@ If send_message fails with a send gate error: call inbox(), reply to or resolve
 
 1. Read the message from `inbox()` or `wait_for_message()`
 2. Do the work - use real code, real files, real results from your project
-3. `reply(message_id, "here's what I did: [concrete changes]")` - use `resolve=true` when the thread is complete
+3. Reply with the right flag:
+   - `reply(message_id, "done: [details]")` — work done, sender might follow up
+   - `reply(message_id, "done: [details]", resolve=true)` — work done, conversation finished
+   - `reply(message_id, "ack, prioritizing [other task] first", defer=true)` — acknowledged but work not done yet. Message stays in your inbox as a reminder.
 4. If sender is online: `wait_for_message()` for follow-ups
 
+When you have multiple pending messages, prioritize by urgency. Use `defer=true` for tasks you'll do later — if you reply without doing the work and don't defer, the message vanishes from your inbox and you will never remember to do it.
+
 ## Cross-user messaging (Gate)
 
 To message a user outside your namespace, use `@username` as the to_agent. Example: `send_message("@maria", "hello")`. The message goes through their Gate - connection approval and guardrails apply. If the connection isn't approved yet, your message is held pending their approval (cap 5, 7-day TTL).

package/skills/inbox/SKILL.md

@@ -52,23 +52,19 @@ If send_message fails with a send gate error: call inbox(), reply to or resolve
 
 1. Read the message
 2. Do the work described in the message - using your project's actual code, real files, real lines
-3. reply(message_id, "here's what I did: [concrete changes with file paths]") - use `resolve=true` when the thread is complete and no further reply is expected
+3. Reply with what you did, choosing the right flag:
+   - `reply(message_id, "done: [details]")` — work done, sender might follow up
+   - `reply(message_id, "done: [details]", resolve=true)` — work done, conversation finished. Notifies the sender.
+   - `reply(message_id, "ack, prioritizing [other task] first", defer=true)` — you acknowledged but haven't done the work yet. The message stays in your inbox as a reminder.
 4. wait_for_message() if the sender is online - stay responsive for follow-ups
 5. If you can't do the work, say specifically what's blocking you. Don't guess about another agent's code.
 
+When you have multiple pending messages, prioritize by urgency. Use `defer=true` for tasks you'll do later — if you reply without doing the work and don't defer, the message vanishes from your inbox and you will never remember to do it.
+
 ## Cross-user messaging (Gate)
 
 To message a user outside your namespace, use `@username` as the to_agent. Example: `send_message("@maria", "hello")`. The message goes through their Gate - connection approval and guardrails apply. If the connection isn't approved yet, your message is held pending their approval (cap 5, 7-day TTL).
 
-## Deferred messages
-
-reply(message_id, content, defer=true) sends a reply but keeps the original message visible in the inbox as "deferred". Use this when:
-- The message needs attention from another agent or a later session
-- You want to acknowledge receipt but can't fully handle it now
-- The human says to mark/defer something for later
-
-Deferred messages survive context compaction - the agent won't forget them.
-
 ## File sharing
 
 Three modes, choose based on context:

package/skills/web/SKILL.md

@@ -73,10 +73,14 @@ After sending to an offline agent, tell the human: "Message sent. [agent] is not
 
 1. Read messages from inbox()
 2. Check the context tag - is this for your chat?
-3. If yes: answer the question, reply(message_id, "[your-tag] your answer")
+3. If yes: do the work, then reply with the right flag:
+   - `reply(message_id, "[tag] done: [details]")` — work done, sender might follow up
+   - `reply(message_id, "[tag] done", resolve=true)` — work done, conversation finished
+   - `reply(message_id, "[tag] ack, will do after [other task]", defer=true)` — acknowledged but work not done yet. Message stays in inbox.
 4. If no: reply(message_id, "For [other-tag] chat", defer=true)
-5. If thread is complete: reply(message_id, "[your-tag] done", resolve=true)
-6. wait_for_message() - stay responsive for follow-ups
+5. wait_for_message() - stay responsive for follow-ups
+
+When you have multiple pending messages, prioritize by urgency. Use `defer=true` for tasks you'll do later — if you reply without doing the work and don't defer, the message vanishes from your inbox and you will never remember to do it.
 
 ## File sharing