Nima Naderi
@nimaJoined Nov 2026covers Feb 19, 2026 – Nov 17, 2026
- sessions
- 1,228
- tokens
- 61.9B
- active days
- 182
- longest streak
- 41 days
- estimated spend
- $38,494
leaderboard ranks
earned titles
The Architect
51% of sessions that edited files started with a plan (half or more earns it)
The Deep Diver
33% of sessions hit a context reset (30% or more earns it)
agents, by share of sessions
- Codex 86%
- Cursor 8%
- Claude Code 5%
- OpenCode 0%
fun factRan 12 agents at once.
how they work
ratios of counts, not volume- Mid-run corrections
- 0.38
- Sessions with a context reset
- 33%
- Tool-call error rate
- 7%
- Started with a plan
- 51%
- Sessions at once
- 1.5×
Recap cards
16 cardsPersona
The Golden-Hour Orchestrator
1,228 sessions in 272 days
Most agents at once
12 at once
sessions side by side, plus 184 subagents
Tokens processed
61.9B
tokens, about $38,494 at API list prices
Longest streak
41 days
in a row, Aug 16 to Sep 25
Longest session
290.2 hrs
of active work in one Codex session
When they prompt
Golden-hour builder
busiest hour 18:00
Manners check
423 pleases
4 thank-yous and 7 sorries in 8,049 prompts
Danger zone
335 × rm -rf
204 force pushes and 8,585 naps. Nothing caught fire.
Time with agents
1,176 hrs
with an agent at work, 1,829 agent-hours in all
Favourite day
Wednesday
the busiest day, 1,455 prompts
Test runs
12,027 runs
of the tests, 59% passed
Bash hall of fame
152,479
shell commands run by agents
Where things broke
20,002
failed tool calls, 7.2% of 277,147
Words typed
325.0K
words in prompts, 35% of them questions
Slash commands
19
slash commands typed
Deep thoughts
308,887
thinking blocks, the longest 15.3 min
Published by @nima from their own AI Insights report. Self-reported, not verified. · see the leaderboard
Find out yours.
One command in your terminal. It reads your history on your machine and makes the recap there. Nothing is uploaded.
$ npx ai-insights@latestYour report stays on your machine. Publishing a profile like this one is optional and sends only the lines you see.