How this command is triggered — by the user, by Claude, or both
Slash command
/maya-toolkit:context-healthThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Context Health Skill
Monitor context window usage and recommend appropriate actions.
## When to Use
- Periodically during long sessions
- Before starting complex tasks
- When user asks about context/memory
- Auto-trigger every 15-20 messages (if supported)
## Execution Steps
1. **Get Context Usage**
- Run `/context` command via Bash
- Parse output for token usage
- Extract key metrics:
- Total usage (tokens and percentage)
- Free space remaining
- Autocompact buffer
- Major consumers (MCP tools, messages, etc.)
2. **Analyze Usage Patterns**
- Calculat...Monitor context window usage and recommend appropriate actions.
Get Context Usage
/context command via BashAnalyze Usage Patterns
Determine Health Status
Healthy (<70%)
Caution (70-85%)
Warning (85-95%)
Critical (>95%)
Provide Recommendations
Based on status, recommend:
Optional Optimization Suggestions
If context getting full:
🔍 Context Health Check
Status: [🟢/🟡/🟠/🔴] [Healthy/Caution/Warning/Critical]
Usage: [XXX]k / 200k tokens ([XX]%)
Free Space: [XX]k tokens ([XX]%)
Breakdown:
- System prompt: [X]k ([X]%)
- System tools: [X]k ([X]%)
- MCP tools: [X]k ([X]%)
- Custom agents: [X]k ([X]%)
- Messages: [X]k ([X]%)
Recommendation: [Action to take]
[Optional optimization suggestions]
If status is Critical (>95%):
/handoff skill/context commandnpx claudepluginhub thamam/experimental-marketplace --plugin maya-toolkit/optimize-contextAnalyzes context window usage against MECW principles, providing token breakdowns, utilization status, and optimization recommendations. Accepts optional path and --detailed flag.
/context-budgetAudits fixed and dynamic context overhead in the current session — scans CLAUDE.md, agents, MCP servers, rules, skills, and history — estimates tokens per component, reports budget usage and headroom, and issues alerts for oversized components or overflow risk.
/context-optimizerDiagnoses context window usage issues, audits MCPs and CLAUDE.md, applies fixes like compaction and disabling unused tools, sets auto-compaction, and reports optimized state.
/contexteRuns built-in /context command to fetch real token metrics, analyzes usage patterns for inefficiencies, and provides tailored optimization recommendations.
/cc-budgetCalculates remaining context window after fixed overhead from CLAUDE.md, rules, skills, and MCP schemas. Shows budget summary table and top consumers. Also supports audit, optimize, anchor-plan, simulate.
/quickPerforms quick context health check: quality score/grade, token overhead, top 3 issues with savings, degradation risk, and action suggestions.