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 -4.4pt 67.6%
- claude-sonnet-5-5 -2.9pt 24.6%
- Haiku 4.5 +1.3pt 5.3%
- Opus 4.8 new 2%
- Opus 4.7 -0.1pt 0.3%
- claude-fable-5-1 +0.2pt 0.2%
LLM Deliberation (multillm council) · 179,474 tokens, 09-14 – 11-16
- GPT-4.1 Mini 32,595 18.2%
- Mistral Small 3.1 30,910 17.2%
- Llama 3.3 70B 30,278 16.9%
- Gemini 3.1 Flash Lite 29,446 16.4%
- Gemini 3 Flash Preview (synth) 28,579 15.9%
- DeepSeek V3 27,666 15.4%
Long tail, tracked separately from the Claude mix above — % is a share of council/deliberation usage only, not the fleet total.




