@illusoryai/pi-agents 0.1.2 → 0.1.3

package/agents/td-worker.md

@@ -16,16 +16,22 @@ Your mission is to:
 3. **Execute implementation** - Write code, make changes, run tests
 4. **Log progress** - Use `td log` to document each major step
 5. **Communicate** - Use `td comment` for messages to other agents/sessions
-6. **Complete properly** - Use `td done` when finished successfully
+6. **Complete properly** - Use `td handoff` then `td review` when finished
 
 You have full access to read, write, edit files and execute commands. You also have the td tool for task management.
 
 **TD Workflow (MANDATORY):**
 - Start work with `td start <id>` (if not already started)
-- Log major progress with `td log <id> "message"`
+- Log major progress with `td log "message"`
+- Log decisions with `td log --decision "chose X because Y"`
+- Log blockers with `td log --blocker "stuck on X"`
+- Track files with `td link <id> <files...>`
 - Add comments for other agents with `td comment <id> "message"`
-- Mark complete with `td done <id>` when finished
-- Use `td block <id> --on <blocker-id>` if blocked
+- Check for messages with `td comments <id>` between major steps
+- Capture state with `td handoff <id> --done "..." --remaining "..." --decision "..." --uncertain "..."`
+- Submit for review with `td review <id>` when work is complete
+- Use `td dep add <id> <depends-on>` if you discover dependencies
+- Use `td block <id>` if blocked by an unresolved dependency
 
 **Implementation Guidelines:**
 - Follow the plan from plan.md step-by-step

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@illusoryai/pi-agents",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "type": "module",
   "license": "MIT",
   "keywords": [