clarify
Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates…
Session start - check progress, suggest next task
$ npx -y skills add mag123c/toktrack --skill next --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nextContext preview
The summary Claude sees to decide when to auto-load this skill.
Session start - check progress, suggest next task
name: next description: Session start - check progress, suggest next task required_context: - .claude/ai-context/architecture.md
Read Planning → Git Log → Analyze → Present → Suggest /clarify
1. **Read Planning**
# Read ONLY the latest planning file (by date prefix YYYYMMDD-) # e.g., 20260205-improvements.md > 20260128-cli-parsers.md # Check checkbox status: [ ] incomplete, [x] complete
2. **Git Log**
git log --oneline -5 git status --short
3. **Analyze**
4. **Present** (table format) | Phase | Status | Progress | |-------|--------|----------| | Phase 0 | ✅ | 5/5 | | Phase 1 | 🔄 | 3/4 |
5. **Suggest**
## Current Status
- Phase: {current_phase}
- Progress: {completed}/{total} tasks
## Next Task
**{task_id}: {task_name}**
{brief_description}
## Action
Run `/clarify` to start: {task_summary}Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)
Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates…
TDD implementation (RED→GREEN→REFACTOR) → verify → review
Multi-agent code review for Rust CLI/TUI. UX Review inactive (terminal UI — no web frontend). Code Review only. Includes Rust/clippy-specific checklist.
Self-healing verification loop (test → clippy → fmt)