INPUT
  ↓
security-check.sh input   (H4: prompt injection, PII, secret)
  ↓
governance-check.sh       (H5: risk, approval, hash-chain audit)
  ↓
agent-metrics.sh          (H6: latency, tokens, cost, retry, status, alert)
  ↓
security-check.sh output  (H4: output redaction/filter)
  ↓
OUTPUT
  ↓
LOG + TRACE + METRICS + AUDIT

Unified wrapper:

```bash
packages/casan-harness/scripts/bash/casan-harness.sh input.txt output.txt agent_step
```

Verification:

```bash
bash packages/casan-harness/tests/run-casan4-harness-tests.sh
```