Tech Executive & AI Advisor
CTO / CIO / Consultant / Applied AI Practitioner
Explore Advisory Services →Bars: repositories with at least one commit that week — 157 at the busiest, out of 223 I build and run. 63% of commits paired with a coding agent. · commits
Bars are input tokens per week (incl. cache-creation/cache-read), left axis; the line is output tokens per week, right axis, independently scaled — not dollar cost. · output tokens
- claude-opus-5-5 -1.3pt 69.5%
- claude-sonnet-5-5 +1.3pt 25.2%
- Haiku 4.5 -0.1pt 4.9%
- Opus 4.7 -0.1pt 0.3%
- claude-fable-5-1 +0.2pt 0.1%
LLM Deliberation (multillm council) · 13,742 tokens, 10-26 – 11-16
- Mistral Small 3.1 3,824 27.8%
- GPT-4.1 Mini 3,433 25%
- Llama 3.3 70B 3,281 23.9%
- Gemini 3 Flash Preview (synth) 3,198 23.3%
- DeepSeek V3 6 0%
Long tail, tracked separately from the Claude mix above — % is a share of council/deliberation usage only, not the fleet total.




