naimkatiman/AI Agent Discipline Linter
Catch agents that skipped research, planning, or verification — by linting their transcript in CI against the 7 Laws of AI Agent Discipline.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| transcript-path | Path to the agent transcript file (JSONL format) | no | "" |
| observations-path | Path to observations.jsonl from a CI session | no | "" |
| strict | Fail the check if any law violations are detected | no | false |
Outputs
| name | description |
|---|---|
| violations | Number of law violations found |
| score | Discipline score (0-100) |
| report | Markdown-formatted report |