Prompt Archaeology

10,497 prompts. 68 days. 53 projects.

What does a body of work look like when you're building with AI every day?

I ran an analysis on my Claude Code conversation history. Not for optimization. For archaeology.

Every prompt I've written since November 2025—extracted, timestamped, clustered by project. The raw material of building with AI.

Three questions drove this:

The Calendar

Each square is a day. Click to see the interleave pattern.

Less
More

The Arc

Three acts emerged from the data.

Act I: Experimentation

Nov 25 – Dec 16

"What can I do with this thing?"

  • mcqmcp — MCQ assessment
  • latinclaude — Latin translation
  • Claudetabs — Browser tabs
  • blendercell — 3D experiments

5-8 projects running simultaneously. Nothing ships yet. Testing boundaries.

Act II: Foundation

Dec 17 – Jan 6

"Build the core asset"

  • sourcelibrary-v2 2,216 prompts
  • translate — Supporting tooling
  • philosopherslibrary — Related archive

One project dominates. Christmas Day: 299 prompts on Source Library.

Act III: Commercialization

Jan 6 – Feb 4

"Ship products for users"

  • playpowerlearn 1,605 prompts
  • lilbookies 1,550 prompts
  • AIED 1,425 prompts in 6 days

Intensity spike. Feb 2: 793 prompts. The experiments became products.

The Interleave

The real signature isn't parallel projects. It's multiplexed attention.

36
seconds avg between switches
1,645
switches on peak day
3-5
projects in parallel

Not time-blocking. Not "morning on X, afternoon on Y." Constant interleaving at sub-minute intervals. Like a DJ mixing between tracks.

The Daily Stream

Each row shows how attention flows between projects throughout a single day. Click any day to see details below.

The Switching Rhythm

Each spike = a context switch. The height shows how many prompts before switching again.

A Day in the Life: Jan 8, 2026

Under the Microscope: Busiest Hour

The Rhythm

When does the work happen?

Methodology

Data extracted from ~/.claude/projects and ~/.claude/history.jsonl using custom Python scripts.

Built with D3.js for visualizations and Python for data extraction.