agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a…
Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled work. Use for scheduled ship follow-through.
$ npx -y skills add BuilderIO/skills --skill factory-watchdog --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/factory-watchdogContext preview
The summary Claude sees to decide when to auto-load this skill.
Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled work. Use for scheduled ship follow-through.
name: factory-watchdog installer-group: factory description: >- Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled work. Use for scheduled ship follow-through.
> Start with the [Factory guide](../../docs/factory/README.md) for workflow > setup and configuration.
Read `.agent-factory/config.yaml`, the optional `skill_prompts.factory-watchdog` entry, and the [Factory configuration reference](https://github.com/BuilderIO/skills/blob/main/docs/factory/configuration.md). 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.
history to confirm the request and any later cancellation or scope change.
ownership, and tasks without configured delivery authorization.
host state immediately before acting and verify the PR is still open and its head matches, or that the named worktree still contains task-owned work.
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.
Small, composable skills for your favorite agent.
Repo: BuilderIO/skills
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a…
Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces,…
Use when running Claude Fable on codebase-heavy or token-heavy work and the user wants Fable…
Apply the same orchestration as `/efficient-fable` to any high-cost frontier model: delegate…
Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to…
Experimental workflow for collecting and triaging product feedback, product telemetry,…