health-sweep

Run sequential pnpm health checks and output a consolidated status table.

3|1|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/miles990/mini-agent --skill health-sweep
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: health-sweep
Source: https://github.com/miles990/mini-agent/tree/main/.claude/skills/health-sweep
Command: npx skills add https://github.com/miles990/mini-agent --skill health-sweep

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of scattered, hard-to-find health-check and janitor commands by providing a single entry point that runs all checks and produces a consolidated report.

Core Features & Use Cases

  • One-command project health sweep: executes a predefined sequence of autonomy, tests, design governance, PR lifecycle, runtime workspace, and evidence/threshold checks in order.
  • Safe dry-run cleanup validation: runs janitor workspace and stash checks without applying changes, surfacing leftovers only.
  • Actionable pass/fail summary: outputs an at-a-glance table plus a final list of items needing attention with suggested next steps; use it before releases, after incidents, or whenever the system behavior looks off.

Example use case: you notice the agent loop feels unstable after multiple changes, so you run the sweep to quickly identify which areas are failing (tests, governance, runtime workspace issues, or leftover git state).

Quick Start

Ask the agent to run health-sweep to perform a read-only health-check cycle and generate a summarized results table.

Frequently Asked Questions about health-sweep

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

FAQPage Schema
How do I run a comprehensive project health check for a TypeScript strict codebase?

Run a full health sweep to execute required pnpm checks in sequence, tolerating missing or failing commands without stopping, and generate a consolidated status table with prioritized next steps.

Can I perform a dry-run cleanup to find leftover git workspace issues before a release?

Yes, the health sweep runs janitor workspace and stash dry-runs without applying changes, safely surfacing leftover git state issues in the final actionable pass/fail summary table.

What is the best way to verify system stability after multiple changes during an OODA-loop?

A project health sweep validates OODA-loop stability by executing autonomy, tests, design governance, and runtime workspace checks, then reporting any failing areas needing immediate attention.

Does the health sweep stop execution if a CI validation command fails?

No, the health sweep tolerates missing or failing commands during CI validation without stopping, collecting all results to output a complete readiness report with suggested remediation steps.

When do I need to run a health sweep for post-incident triage?

Run a health sweep after incidents to quickly identify failing areas across tests, governance, and runtime workspace, using the consolidated pass/fail summary to guide triage and recovery.