Imported from majiayu000/claude-skill-registry-data (context-management/context-monitor/SKILL.md). Install upstream with npx skills add majiayu000/claude-skill-registry-data --skill context-monitor. Copyright stays with the author.

Context Usage Monitor

Name: context-monitor
Author: majiayu000

Purpose

Monitor and warn about context usage to prevent context exhaustion.

Usage Thresholds

30k tokens: First warning (Yellow)
50k tokens: Strong warning (Orange)
70k tokens: Critical warning (Red) - Consider /clear

Monitoring Points

After each agent invocation
Before complex tasks
When reading large files

Warning Messages

Yellow (30k)

⚠️ Context Usage: ~30k tokens
Consider focusing on current task only.

Orange (50k)

🟠 Context Usage: ~50k tokens
Recommend completing current task then /clear.

Red (70k+)

🔴 Context Usage: 70k+ tokens
CRITICAL: Use /clear soon to prevent errors.
Save important context before clearing.

Best Practices

Use subagents to preserve main context
Clear context between major features
Avoid reading unnecessary large files
Use Task tool for complex searches

Context-Saving Commands

Before /clear, save important info:

# Save current branch and status
git status > /tmp/context_save.txt
git diff --staged >> /tmp/context_save.txt

# After /clear, restore context:
cat /tmp/context_save.txt

Skill Version: v1.0 Last Updated: 2025-12-25 Project: career_ios_backend

{ "ocm": "1", "id": "majiayu000-claude-skill-registry-data-context-monitor", "kind": "skill", "name": "context-monitor", "description": "Monitors context token usage and warns when approaching limits. Automatically activates when context usage exceeds thresholds (30k, 50k, 70k tokens). Provides recommendations for context management and /clear usage. Auto-activates based on token usage, no specific keywords needed.", "publisher": "majiayu000", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Monitors context token usage and warns when approaching limits. Automatically activates when context usage exceeds thresholds (30k, 50k, 70k tokens). Provides recommendations for context management and /clear usage. Auto-activates based on token usage, no specific keywords needed." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/majiayu000/claude-skill-registry-data", "path": "context-management/context-monitor/SKILL.md", "ref": "f863c11651055f498e1466492dc2a0d95721d2d5", "url": "https://github.com/majiayu000/claude-skill-registry-data/blob/f863c11651055f498e1466492dc2a0d95721d2d5/context-management/context-monitor/SKILL.md", "key": "majiayu000/claude-skill-registry-data/context-management/context-monitor/SKILL.md" }, "allowed_tools": [ "Read" ] }, "instructions": "# Context Usage Monitor\n\n## Purpose\nMonitor and warn about context usage to prevent context exhaustion.\n\n## Usage Thresholds\n- **30k tokens**: First warning (Yellow)\n- **50k tokens**: Strong warning (Orange)\n- **70k tokens**: Critical warning (Red) - Consider /clear\n\n## Monitoring Points\n1. After each agent invocation\n2. Before complex tasks\n3. When reading large files\n\n## Warning Messages\n\n### Yellow (30k)\n```\n⚠️ Context Usage: ~30k tokens\nConsider focusing on current task only.\n```\n\n### Orange (50k)\n```\n🟠 Context Usage: ~50k tokens\nRecommend completing current task then /clear.\n```\n\n### Red ", "cost": { "context_tokens": 311 } }

context-monitor

About