this extension makes sure the agent actually finishes everything you asked:
1. **splits your requests**: breaks compound messages into separate tasks so nothing gets lost.
2. **keeps open tasks visible**: pins still-unfinished tasks into the prompt on every turn, even after compaction.
3. **checks the work**: a small background model watches what gets done and stages tasks for completion when work lands or tests pass.
4. **prevents false claims**: the background model cannot mark tasks "done" on its own. tasks only close when verified by real passing commands or when you accept them.
4. **safe completions**: for code changes, tasks only close if tests and checks actually pass. for conversational requests, tasks close once the model verifies they're satisfied and uncontested. you can always manually adjust or reopen anything with `/threads`.
## requirements
- Prime Agent 0.9.1, or a compatible extension API