# Context Optimizer

> Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.

- Skill: `henriquescastilho/context-optimizer` (Agent Skill)
- Install (CLI): `npx skillmds@latest add henriquescastilho/context-optimizer`
- Raw SKILL.md: https://api.skillmd.com/api/skills/henriquescastilho/context-optimizer/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Finance & Business
- Author: henriquescastilho (https://skillmd.com/u/henriquescastilho)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/henriquescastilho/context-optimizer

---


# Context Optimizer

Manage your context window and token budget effectively.

## Quick Diagnosis

1. Run `/context` to check current usage
2. If > 70% → compact now before it degrades
3. If > 90% → you're in the "dumb zone", compact immediately

## Optimization Strategies

### Immediate

| 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 |

### Configuration

Set proactive auto-compaction:
```json
{
  "env": {
    "CLAUDE_AUTOCOMPACT_PCT_OVERRIDE": "50"
  }
}
```

### MCP Audit

Keep <10 MCPs enabled, <80 tools total. Each MCP adds overhead to every request.

```bash
/mcp          # List active servers
# Disable what you're not using
```

### Prompt Engineering for Token Efficiency

- Scope your prompts: "In src/auth/, fix the login bug"
- Provide constraints: "Don't modify the middleware"
- Give acceptance criteria: "Should return 429 after 5 attempts"
- Avoid vague prompts: "Fix the code" (forces Claude to read everything)

### Subagent Delegation

Heavy operations that generate lots of output should go to subagents:

- Test suite output → subagent
- Large file exploration → subagent
- Documentation generation → subagent
- Log analysis → subagent

The main session stays clean while subagents handle the volume.

## Context Budget Planning

| 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 |

## CLAUDE.md Optimization

- Root CLAUDE.md: < 60 lines ideal, < 150 max
- Move package-specific info to package-level CLAUDE.md
- Move personal preferences to CLAUDE.local.md
- Remove obvious or rapidly-changing information

## When Context Is Degraded

Signs:
- Claude repeats itself or forgets earlier context
- Responses become generic or lose project-specific knowledge
- Tool calls start failing for reasons that worked earlier

Fix:
1. Manual `/compact`
2. If still bad: new session with `/resume`
3. For recurring issues: reduce CLAUDE.md size, disable MCPs