Monitor explicitly authorized software delivery tasks, verify which work has stopped, and send reminders only when a concrete next step is due and the configured notification policy allows it.
Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled work. Use for scheduled ship follow-through.
Review the instructions the agent will receive before you install.
Start with the Factory guide for workflow setup and configuration.
Read .agent-factory/config.yaml, the optional
skill_prompts.factory-watchdog entry, and the Factory configuration reference. Monitor only configured projects and authorized delivery handoffs. The prompt cannot grant notification or delivery authority. A task title, branch, PR, green check, or agent summary is not authorization.
Send a reminder only when the notification policy permits it and current live evidence shows a concrete next step is due. Check task history for an unchanged reminder. Use the configured destination, cadence, wording, and rate limit.
Keep the task owner responsible for merge, post-merge verification, and cleanup
unless the config explicitly assigns those actions elsewhere. If target or
state cannot be proven, do not message. Report DONT_NOTIFY when nothing
meaningful changed.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Guide public skill additions and updates through file placement, catalog documentation, installation discovery, integration settings, and validation. Distinguish ordinary skills from instruction-based, app-backed, and generated skills so each receives the appropriate checks.
Monitor another AI agent’s work and independently investigate the same task. Compare the original request with actual changes and test evidence, report gaps and concrete follow-up steps, and make limited fixes when authorized.
Open Agent-Native apps beside the conversation through Dispatch MCP, a connection for app tools. Create or edit content using the current screen and selection, then read saved results back to confirm the changes.
Organize large coding tasks with Claude Fable directing lower-cost subagents. Delegate bounded research, edits, and tests, then have Fable verify evidence, resolve conflicting findings, integrate changes, and review the final result.
Organize work so an expensive AI model handles planning, judgment, and final review while cheaper helper agents perform bounded research, coding, and testing. Define ownership and verification requirements, then inspect the evidence and integrate their results centrally.
Configure a software delivery workflow that turns selected feedback and maintenance signals into verified, reviewed changes. Define information sources, schedules, working directories, and separate permissions for actions such as implementation, merging, deployment, and notifications.