swarm-ai-safety EXECUTE NOW
Scenario: $ARGUMENTS
If no scenario provided, ask which scenario to check.
Step 1: Validate scenario file
- Check that the scenario file exists in
scenarios/ - Read and parse the YAML
- Report: agent types, governance config, topology, epoch/step counts
Step 2: Run short
python -m swarm run scenarios/$SCENARIO --seed 42 --epochs 5 --steps 5
Step 3: Check results
- Verify the run completed without exceptions
- Read the output summary
- Check metric sanity:
pvalues in [0, 1]- Welfare is finite and reasonable
- Toxicity rate is in [0, 1]
- Acceptance rate is in [0, 1]
- No NaN or Inf values
Step 4: Report
## Sanity Check: {scenario}
Status: GO / NO-GO
Runtime: {seconds}s
Metrics:
- Welfare: {value}
- Toxicity: {value}
- Acceptance rate: {value}
- Quality gap: {value}
{If NO-GO: describe the issue and suggest fix}
{If GO: ready for full sweep with --seeds N}