feat(marketplace): add lean/full profile switching for token optimization

- Add marketplace-lean.json (6 plugins) and marketplace-full.json (12 plugins)
- Add .mcp-lean.json (gitea only) and .mcp-full.json (5 servers)
- Create scripts/switch-profile.sh for easy profile switching
- Update sprint-status.md with conditional skill loading
- Set lean profile as default (~14k token savings)

Lean profile includes: projman, git-flow, pr-review, clarity-assist,
code-sentinel, doc-guardian

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

plugins/projman/commands/sprint-status.md

@@ -24,7 +24,7 @@ Check current sprint progress, identify blockers, and show execution status. Opt
 ```
 /sprint-status              # Text-based status report
 /sprint-status --diagram    # Include Mermaid dependency diagram
-/sprint-status --tokens     # Show token budget estimation report
+/sprint-status --tokens     # Include token budget estimation report
 ```
 
 ## Workflow
@@ -46,11 +46,7 @@ That's it. No dependency analysis, no token estimation, no progress comment pars
 
 ### If --tokens flag, THEN ALSO:
 11. Load `skills/token-budget-report.md`
-12. **Generate Token Budget Report** - Execute `skills/token-budget-report.md` estimation model
+12. Generate token estimation report
-    - Phase: STATUS (read-only snapshot, not a workflow boundary)
-    - List MCP servers from `.mcp.json` with static overhead estimates
-    - Show current session cost estimate based on skills loaded so far
-    - Display formatted report per the skill's Display Format section
 
 ## Output Format