Skip to content
Back to skills

Factory Watchdog

ASecurity

Monitor authorized delivery tasks for verified stalls.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 9, 2026
ai-agents

Works with

  • claude code
  • cursor

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned November 9, 2026

npx -y skills add jaydubya818/MissionControl --skill factory-watchdog --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Factory Watchdog?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Factory Watchdog
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jaydubya818-factory-watchdog/badge)](https://www.skillsdirectory.com/skills/jaydubya818-factory-watchdog)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: factory-watchdog
description: "Monitor authorized delivery tasks for verified stalls."
license: MIT
compatibility: "Works in Claude Code, Codex, Cursor, and Agent Skills-compatible harnesses when the required host tools are available."
metadata:
  author: Builder.io
  source: BuilderIO/skills
  source-commit: f4f10b8d513476c24bd995ceac5294bcdd6ee15c
  owner: software-factory
  risk: medium
  capabilities: builderio,factory-monitoring
  installer-group: factory
---

# Factory Watchdog

> Start with the [Factory guide](../factory/references/factory-guide.md) for workflow
> setup and configuration.

Read `.agent-factory/config.yaml`, the optional
`skill_prompts.factory-watchdog` entry, and the [Factory configuration reference](../factory/references/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.

## Find actionable stopped work

- Find candidates through the configured host and read enough user-authored
  history to confirm the request and any later cancellation or scope change.
- Skip active work, explicit waits, completed or cancelled tasks, ambiguous
  ownership, and tasks without configured delivery authorization.
- For stopped work, identify its task-owned PR, branch, or worktree. Check live
  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.

## Notify only on a verified next step

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.

Files in this skill

  • LICENSE1 KB
  • SKILL.md2 KB
  • agents/openai.yaml195 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.