Exploration Log

Building daily to find
what's worth a lifetime.

Exploring the unknown to find what's worth building for a lifetime. 9+ years crypto quant → AI agent explorer.

0+Projects

0Domains

★ 0Stars

0BLLM Tokens

Explore Projects→About Me

Contribution Activity

data through 2026-08-09

GITHUB commits & PRs

LessMore

AugSepOctNovDecJanFebMarAprMayJunJulAug

TOKENS every session — including work that never became a commit

no local logsLessMore

110B

Tokens

265 / 430

Active days

696K

Messages

MODELS where those tokens went

surviving logs since 2026-03-11

claude-opus-5 19B · 24%claude-opus-4-7 19B · 24%claude-fable-5 14B · 18%gpt-5.6-sol 13B · 16%claude-opus-4-8 7B · 9%claude-sonnet-5 6.6B · 8%gpt-5.4 1.1B · 1%

100% of these tokens went to repositories I haven't published.

Records reach back to 2024-11-10; data through 2026-08-09. Hollow days are gaps no surviving log or submission covers.

Recent Explorations

View All →

lol-arena

League of Legends Arena (Cherry mode) DPS calculator + theorycrafting toolkit. Scrapes all champions, items, augments, runes; computes build stats and DPS.

Python

dagulint

Local-first lint, fmt, diff for dagu workflow YAML — DAGU001-020 rule catalogue, deterministic output, single binary.

Rust

evaltrack

Local-first regression and trend CLI for promptfoo eval histories — the git log + git diff for LLM eval outputs.

TypeScript

difyctl

★ 1

Lint and semantically diff Dify workflow DSL (YAML) from the command line. CI-friendly, single binary.

skilldigest

Static analyzer for AI agent skill libraries. Finds dead/bloated/conflicting skills, counts tokens, gates CI. Single Rust binary.