agent-team-task-stale

Identify stale in_progress or blocked tasks using the agent-team binary.

2|Updated May 10, 2026
One-click install
npx skills add https://github.com/tae2089/agent-team --skill agent-team-task-stale
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-team-task-stale
Source: https://github.com/tae2089/agent-team/tree/main/skills/agent-team-task-stale
Command: npx skills add https://github.com/tae2089/agent-team --skill agent-team-task-stale

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Detects old in_progress or blocked tasks to enable operational recovery in daemonless setups, reducing manual investigation and downtime.

Core Features & Use Cases

  • Stale-task detection: identifies tasks in in_progress or blocked states that exceed a specified age threshold.
  • Run-scoped analysis: targets a specific run via the --run flag to isolate impact and recovery actions.
  • Configurable filtering: supports --older-than, --limit, and --after-version to refine results and guard against unbounded queries.

Quick Start

Run the task stale command for a given run to surface overdue tasks and plan recovery steps.

Frequently Asked Questions about agent-team-task-stale

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify stale in_progress or blocked tasks without a daemon?

You can identify stale in_progress or blocked tasks without a daemon by using a stale-task detection command that filters tasks exceeding a specified age threshold and generates a structured report for operational recovery.

Can I filter stale task detection to a specific run?

Yes, you can scope stale task detection to a specific run by applying the --run parameter, which isolates the impact analysis and recovery actions to only the tasks within that targeted execution.

How do I configure age thresholds and limits when surfacing stalled tasks?

To configure stalled task surfacing, apply the --older-than parameter to set the age threshold, and use --limit and --after-version to refine results and guard against unbounded queries.

What is the best way to recover old blocked tasks in daemonless setups?

The best way to recover old blocked tasks in daemonless setups is to run a stale-task inspection that filters by age and run, reducing manual investigation by surfacing overdue tasks in a structured report.

What parameters are required to run a stale task inspection?

Running a stale task inspection requires the --run parameter to target a specific execution and the --older-than parameter to define the age threshold, while --limit and --after-version are optional filters.