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 GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
transcript-pathPath to the agent transcript file (JSONL format)no""
observations-pathPath to observations.jsonl from a CI sessionno""
strictFail the check if any law violations are detectednofalse
namedescription
violationsNumber of law violations found
scoreDiscipline score (0-100)
reportMarkdown-formatted report