> ## Documentation Index
> Fetch the complete documentation index at: https://docs.acmeagentsupply.com/llms.txt
> Use this file to discover all available pages before exploring further.

# RadCheck Overview

> Read-only reliability scanning for AI agents

# RadCheck

RadCheck is ACME's free reliability scanner. It performs a read-only assessment of your agent environment and produces a 0-100 reliability score.

## What RadCheck Does

<Info>
  RadCheck is **read-only**. It scans your environment but makes no changes. No agents are installed, no processes are started, no configurations are modified.
</Info>

RadCheck examines your agent system for reliability risk factors:

* **Stall risk** — Patterns that indicate potential hangs or infinite loops
* **Silence gaps** — Unexpected periods of inactivity that may indicate failures
* **Compaction pressure** — Context window utilization and memory patterns
* **Hygiene** — Configuration best practices and common misconfigurations

## Running RadCheck

```bash theme={null}
acme radcheck
```

The scan typically completes in under 30 seconds. Output includes:

```
RadCheck Reliability Scan
=========================
Overall Score: 72 / 100 (YELLOW)

Components:
  Stall Risk:        18/25  ✓
  Silence Gaps:      15/25  ⚠
  Compaction:        22/25  ✓
  Hygiene:           17/25  ⚠

Findings:
  [WARN] Silence gap detected: 47s between context updates
  [WARN] Missing retry configuration in provider fallback
  [OK]   No stall patterns detected
  [OK]   Context utilization within bounds
```

## Score Bands

| Score  | Band      | Interpretation                           |
| ------ | --------- | ---------------------------------------- |
| 80-100 | 🟢 GREEN  | Healthy. Continue normal operations.     |
| 60-79  | 🟡 YELLOW | Monitor closely. Review warnings.        |
| 40-59  | 🟠 ORANGE | Action recommended. Reliability at risk. |
| 0-39   | 🔴 RED    | Critical. Immediate attention needed.    |

## When to Run RadCheck

* **Before deploying** a new agent configuration
* **After incidents** to identify contributing factors
* **Periodically** as part of reliability hygiene (weekly recommended)
* **When onboarding** to get a baseline score

## From RadCheck to Sentinel

RadCheck tells you your current state. [Sentinel](/products/sentinel/overview) provides ongoing protection.

Think of it this way:

* **RadCheck** = Point-in-time snapshot (like a blood test)
* **Sentinel** = Continuous monitoring (like a heart monitor)

Most teams start with RadCheck to understand their baseline, then add Sentinel for runtime protection.

## CLI Reference

```bash theme={null}
# Basic scan
acme radcheck

# JSON output (for CI/CD integration)
acme radcheck --format json

# Scan specific agent
acme radcheck --agent my-agent-name

# Verbose output with all checks
acme radcheck --verbose
```

## Next Steps

<CardGroup cols={2}>
  <Card title="Score Explained" icon="chart-bar" href="/products/radcheck/score-explained">
    Deep dive into how each score component is calculated.
  </Card>

  <Card title="Sentinel" icon="shield" href="/products/sentinel/overview">
    Add runtime protection after establishing your baseline.
  </Card>
</CardGroup>