How this skill is triggered — by the user, by Claude, or both
Slash command
/b17z-sage:sage-sessionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
On session start, Sage automatically injects context. Here's how to use it.
On session start, Sage automatically injects context. Here's how to use it.
On your first Sage tool call each session, Sage automatically injects:
.sage/system/objective.md, constraints.md (v4.0)This happens automatically when you call sage_health(), sage_version(), sage_list_knowledge(), etc.
sage_health()
This:
After sage_health(), load a relevant checkpoint:
sage_search_checkpoints(query="what you're continuing")
sage_load_checkpoint(checkpoint_id="...")
sage_list_todos()
Review any persistent reminders from previous sessions.
1. sage_health() # Context injection + diagnostics
2. sage_list_todos() # Check reminders (optional)
3. sage_load_checkpoint() # Restore deep context (if needed)
4. Begin work
Reference Sage data directly with @sage:// syntax:
@sage://system/objective.md # Current goal
@sage://checkpoint/jwt-research # Checkpoint by ID
@sage://knowledge/auth-patterns # Knowledge item
@sage://failure/jwt-localstorage # Recorded failure
This works without tool calls in Claude Code's @ mentions.
npx claudepluginhub joshuarweaver/cascade-featured --plugin b17z-sageGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Resolves in-progress git merge or rebase conflicts by analyzing history, understanding intent, and preserving both changes where possible. Runs automated checks after resolution.