Tech Executive & AI Advisor
CTO / CIO / Consultant / Applied AI Practitioner
Explore Advisory Services →Bars: repositories with at least one commit that week — 156 at the busiest, out of 202 I build and run. 66% 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 -6.9pt 72.7%
- claude-sonnet-5-5 -0.3pt 21.7%
- Haiku 4.5 +6.8pt 5.3%
- Opus 4.7 new 0.2%
- Opus 4.8 new 0.1%
- claude-fable-5-1 new 0.1%
LLM Deliberation (multillm council) · 204,555 tokens, 08-31 – 10-19
- Gemini 3.1 Flash Lite 36,584 17.9%
- GPT-4.1 Mini 36,484 17.8%
- DeepSeek V3 34,135 16.7%
- Llama 3.3 70B 33,310 16.3%
- Mistral Small 3.1 32,277 15.8%
- Gemini 3 Flash Preview (synth) 31,765 15.5%
Long tail, tracked separately from the Claude mix above — % is a share of council/deliberation usage only, not the fleet total.




