Claude-skill-registry context-monitor
install
source · Clone the upstream repo
git clone https://github.com/majiayu000/claude-skill-registry
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/context-monitor" ~/.claude/skills/majiayu000-claude-skill-registry-context-monitor && rm -rf "$T"
manifest:
skills/data/context-monitor/SKILL.mdsource content
Context Usage Monitor
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