القائمة
Generate detailed token usage report with threshold analysis and recommendations
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Guide for writing clear, descriptive commit messages
Merge task branch to base branch with linear history (works from task worktree)
MANDATORY: Use instead of `git rebase` - provides automatic backup and conflict recovery
MANDATORY: Use instead of `git rebase -i` for squashing - unified commit messages
Analyze mistakes with conversation length as potential cause (CAT-specific)
Run scheduled retrospective analysis, derive action items, and track effectiveness
| name | cat:token-report |
| description | Generate detailed token usage report with threshold analysis and recommendations |
Display a compact token usage report showing per-subagent breakdown with context utilization, health status, and duration. Essential for understanding session resource consumption at a glance.
CRITICAL: This skill requires hook-based pre-computation. Check context for:
PRE-COMPUTED TOKEN REPORT:
Output the table EXACTLY as provided. Do NOT modify alignment or recalculate values.
Example pre-computed output:
╭───────────────────┬────────────────────────────────┬──────────┬──────────────────┬────────────╮
│ Type │ Description │ Tokens │ Context │ Duration │
├───────────────────┼────────────────────────────────┼──────────┼──────────────────┼────────────┤
│ Explore │ Explore codebase │ 68.4k │ 34% │ 1m 7s │
│ general-purpose │ Implement fix │ 90.0k │ 45% ⚠️ │ 43s │
│ general-purpose │ Refactor module │ 170.0k │ 85% 🚨 │ 3m 12s │
├───────────────────┼────────────────────────────────┼──────────┼──────────────────┼────────────┤
│ │ TOTAL │ 328.4k │ - │ 5m 2s │
╰───────────────────┴────────────────────────────────┴──────────┴──────────────────┴────────────╯
FAIL immediately with this message:
ERROR: Pre-computed token report not found.
The hook precompute-token-report.sh should have provided the table data.
Do NOT attempt manual computation - the alignment requires deterministic
Python-based calculation.
Possible causes:
1. Session file not found
2. No subagent data in session
3. Hook execution failed
Try running /cat:token-report again or check session status.
Do NOT proceed to manual extraction or table building.
The pre-computed table uses these specifications:
Column widths (fixed):
| Column | Width | Content |
|---|---|---|
| Type | 17 | Subagent type (truncated with ...) |
| Description | 30 | Task description (truncated with ...) |
| Tokens | 8 | Formatted count (68.4k, 1.5M) |
| Context | 16 | Percentage with emoji indicator |
| Duration | 10 | Formatted time (1m 7s) |
Context indicators (INSIDE column):
| Context % | Display | Meaning |
|---|---|---|
| < 40% | "34%" | Healthy - plenty of headroom |
| >= 40% and < 80% | "45% ⚠️" | Warning - above soft target |
| >= 80% | "85% 🚨" | Critical - approaching limit |
Box characters:
╭─┬─╮├─┼─┤╰─┴─╯│Before outputting the table, verify:
# BAD - Manual jq extraction and formatting
jq -s '...' "$SESSION_FILE"
# Then manually building table rows
# GOOD - Use pre-computed results only
# Output exactly what the hook provided
# BAD - "Fixing" spacing or alignment
│ Type │ # Wrong - modified padding
# GOOD - Copy exactly as provided
│ Type │ # Correct - preserved padding
cat:monitor-subagents - Uses token data for health checkscat:decompose-task - Triggered when context reaches critical levelscat:learn-from-mistakes - Uses token data for context-related analysis