aretedriver/Context Hygiene

Audit LLM conversation context window hygiene. Detects staleness, contradictions, deadweight, and compression opportunities in chat transcripts and AI instruction files.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
filesFiles or glob patterns to audit (space-separated). Example: "CLAUDE.md conversations/*.jsonl" yes
fail-underMinimum grade threshold (A/B/C/D/F). The action fails with exit code 1 if any audited file scores below this threshold. noC
formatOutput format: rich (default), json, or sarif. Use sarif for GitHub Code Scanning integration. norich
versionVersion of context-hygiene to install from PyPI. Default: latest. no""
namedescription
gradeOverall grade of the worst-audited file
files-auditedNumber of files successfully audited