Context Budget Optimizer

Framework: The Token Efficiency Matrix Worth $200/hr consultant time. Yours for $19.

What This Skill Does

Audits your agent's token usage across every context layer, identifies where you're burning budget on bloat, and produces a 3-week cost reduction roadmap with concrete implementation steps.

Problem it solves: Power users hitting $200-500/month in AI costs often have 60-70% waste baked into their context. Most of it is invisible: stale files in system prompts, redundant skill loading, oversized memory files, wrong model choices. The Token Efficiency Matrix makes the waste visible and rankable.

The Token Efficiency Matrix

A 4-quadrant audit tool that scores every context element by cost (token weight) and ROI (value delivered per token). High cost + low ROI = cut first.

The Matrix

                    HIGH ROI
                       │
          KEEP         │      OPTIMIZE
       (High ROI,      │   (High ROI,
        Low Cost)      │    High Cost)
                       │
LOW COST ──────────────┼────────────────── HIGH COST
                       │
          AUDIT        │       CUT
       (Low ROI,       │   (Low ROI,
        Low Cost)      │    High Cost)
                       │
                    LOW ROI

Action by quadrant:

• KEEP: Don't touch. It's working efficiently.
• OPTIMIZE: Compress or lazy-load. Value is there, just expensive.
• AUDIT: Review quarterly. Low cost so not urgent, but ROI should be questioned.
• CUT: Kill immediately. You're paying for nothing.

Phase 1: Context Inventory

Before scoring, map everything that's in your agent's context.

Context Layers to Audit

Layer A: System Prompt / SOUL.md / Identity files
Layer B: Active skills (loaded per session)
Layer C: Memory files (MEMORY.md, daily notes)
Layer D: Project files injected at startup
Layer E: Tool outputs / MCP responses in context
Layer F: Chat history (conversation turns kept in context)
Layer G: Code or data files read into context

Inventory Template

For each item in your context, fill this in:

*Daily Cost = (Est. Tokens / 1M) × model_rate × sessions_per_day

Token estimation cheatsheet:

• 1 page of text ≈ 500-700 tokens
• 1 SKILL.md file ≈ 800-2,000 tokens
• 1 code file (100 lines) ≈ 1,200-1,800 tokens
• 1 MEMORY.md (well-maintained) ≈ 500-1,500 tokens
• 1 MEMORY.md (neglected/bloated) ≈ 3,000-8,000 tokens