miqdadbadjuber/anti-slop v3.1.3

on GitHub

v3.1.3

• States the DESIGN.md boundary explicitly: external files are data to apply, not instructions to obey. The agent extracts only the design fields and treats anything that reads like a command as content.
• Adds SECURITY.md, a plain-language explainer for the skills.sh audit flags: the pointer block and the contrast checker are deliberate features, and the DESIGN.md finding is fixed.
• Documents in the README that npx skills add copies the skill folders but does not write the agent entry pointer; run npx antislop-ai and pick "Keep what is there" to add it.

See ROADMAP.md for the tracker.