Loading npm security reports…
Claude Code that gets sharper every session: the persistent-memory and runtime-discipline layer built on the 7 Laws of AI Agent Discipline. It grounds every edit in real facts before it lands and, through the Mulahazah engine, turns each fix into a reusab
LPM treats this as warn-only first-party agent extension lifecycle risk. No confirmed malicious or unconsented install-time attack surface. Explicit installer use configures Claude hooks/MCP and can add package content to named agent rule files.
Package source references dynamic require/import behavior.
bin/check-test-imports-only.mjsView on unpkg · L105Package source references weak cryptographic algorithms.
bin/harvest-friction.mjsView on unpkg · L170Package ships non-JavaScript build or shell helper files.
bin/analyze.shView on unpkgThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
bin/install.mjsView on unpkgPackage source references dynamic require/import behavior.
bin/check-test-imports-only.mjsView on unpkg · L105Package ships non-JavaScript build or shell helper files.
bin/analyze.shView on unpkgThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
bin/install.mjsView on unpkgPackage source references weak cryptographic algorithms.
bin/harvest-friction.mjsView on unpkg · L170