Skip to content

Conversation

@devill
Copy link
Collaborator

@devill devill commented Jan 24, 2026

Summary

  • Adds new pattern: Contextual Prompts - embed guidance directly in script outputs (error messages, CLI responses) instead of front-loading instructions in CLAUDE.md
  • This is a generalization of the principle behind Habit Hooks

Discussion Requested

@lexler - I'd like to discuss whether we should restructure the relationship between these related patterns:

  • Contextual Prompts (this new one) - the fundamental principle of putting guidance where it will be seen at the right moment
  • Habit Hooks - a more specific implementation that uses hooks to guarantee scripts run and detect violations
  • Reminders - techniques for injecting reminders into conversations
  • Hooks - the infrastructure pattern that enables Habit Hooks

Currently I've set up habit-hooks -->|uses| contextual-prompts and contextual-prompts <-->|similar| reminders, but there might be a cleaner way to organize this family of patterns. Open to suggestions!

Test plan

  • npm run validate passes (relationships are valid)
  • Pattern renders correctly on site

🤖 Generated with Claude Code

devill and others added 2 commits January 24, 2026 11:55
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants