yiheinchai/Trickle Agent Eval
Zero-code agent reliability scoring. Runs your app with trickle, evaluates on 5 dimensions, posts results as PR comment.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| command | Command to run with trickle (e.g., "python my_agent.py") | yes | — |
| fail-under | Minimum eval score (0-100). Fails if below. | no | 0 |
| security-scan | Run security scan | no | false |
| compliance-report | Generate compliance audit report | no | false |
Outputs
| name | description |
|---|---|
| score | Overall eval score (0-100) |
| grade | Letter grade (A-F) |
| passed | Whether score met threshold |