Menu
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | context-optimizer |
| description | Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget. |
Manage your context window and token budget effectively.
/context to check current usage| Action | Saves | When |
|---|---|---|
/compact | 30-50% context | At task boundaries |
| Disable unused MCPs | ~5% per MCP | When switching domains |
| Use subagents for exploration | Keeps main context clean | Heavy search/read tasks |
Fresh session via /resume | 100% reset | When starting unrelated work |
Set proactive auto-compaction:
{
"env": {
"CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50"
}
}
Keep <10 MCPs enabled, <80 tools total. Each MCP adds overhead to every request.
/mcp # List active servers
# Disable what you're not using
Heavy operations that generate lots of output should go to subagents:
The main session stays clean while subagents handle the volume.
| Phase | Target Usage | Action If Over |
|---|---|---|
| Planning | < 20% | Keep plans concise |
| Implementation | < 60% | Compact between files |
| Testing | < 80% | Delegate to subagent |
| Review | < 90% | Start fresh session |
Switch response style based on context:
Signs:
Fix:
/compact/resumeSkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules. Use when permission prompts are slowing you down or after sessions with many denials.
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 5 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
Prevent destructive operations using Claude Code hooks. Three modes — cautious (warn on dangerous commands), lockdown (restrict edits to one directory), and clear (remove restrictions). Uses PreToolUse matchers for Bash, Edit, and Write.
Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's "Unreasonable Effectiveness of HTML" — favors information density and shareability over markdown-only outputs.