Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From conserve
Analyzes context window usage against MECW principles, providing token breakdowns, utilization status, and optimization recommendations. Accepts optional path and --detailed flag.
npx claudepluginhub athola/claude-night-market --plugin conserveHow this command is triggered — by the user, by Claude, or both
Slash command
/conserve:optimize-contextThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Optimize Context Usage Analyzes context window usage and provides optimization recommendations based on Maximum Effective Context Window (MECW) principles. ## Usage ## What It Does 1. **Context Pressure Assessment**: Evaluates current context utilization 2. **MECW Compliance Check**: Validates against MECW principles 3. **Optimization Recommendations**: Suggests specific improvements 4. **Token Budget Analysis**: Breaks down token usage by component ## MECW Thresholds | Utilization | Status | Action | |-------------|--------|--------| | < 30% | Optimal | No action needed | | 30-50...
/context-budgetAnalyzes context window usage across agents, skills, MCP servers, and rules to find optimization opportunities, producing a Context Budget Report with recommendations.
/context-budgetAnalyzes context window usage across agents, skills, MCP servers, and rules in Claude Code setups, producing a report with optimization recommendations to reduce token overhead.
/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.
/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.
/quickPerforms quick context health check: quality score/grade, token overhead, top 3 issues with savings, degradation risk, and action suggestions.
Share bugs, ideas, or general feedback.
Analyzes context window usage and provides optimization recommendations based on Maximum Effective Context Window (MECW) principles.
# Analyze current session context
/optimize-context
# Analyze specific skill or directory
/optimize-context skills/my-skill
# Deep analysis with recommendations
/optimize-context --detailed
| Utilization | Status | Action |
|---|---|---|
| < 30% | Optimal | No action needed |
| 30-50% | Good | Monitor growth |
| 50-70% | Warning | Consider optimization |
| > 70% | Critical | Immediate action required |
/optimize-context
# Output:
# Context Optimization Report
# ==========================
# Current Usage: 45% (Good)
# Estimated Tokens: 12,500
#
# Recommendations:
# - Consider extracting code examples to scripts/
# - 3 skills exceed recommended token budget
/optimize-context skills/context-optimization --detailed
# Full breakdown with per-module analysis
For reading context in headless/automated Claude Code sessions:
# Get context breakdown with JSON output
claude -p "run /context" --verbose --output-format json
# Two-call pattern for reliable execution
# (Claude doesn't always execute /context on first prompt)
SESSION_ID=$(claude -p "ready" --output-format json | jq -r '.session_id')
claude --continue "$SESSION_ID" -p "/context" --verbose --output-format json
Key flags:
--verbose: Includes categorical token breakdown--output-format json: Machine-parseable output--continue: Resumes existing session for reliable command executionExample JSON output:
{
"context": {
"total_tokens": 45000,
"usage_percent": 22.5,
"breakdown": {
"system": 8000,
"conversation": 32000,
"tools": 5000
}
}
}
Works with conservation plugin skills:
context-optimization - Core MECW implementationtoken-conservation - Token reduction strategiesoptimizing-large-skills - Modularization patternspython3 ${CLAUDE_PLUGIN_ROOT}/scripts/growth_analyzer.py "${1:-.}"