# Henry Cooper

I direct AI coding agents, and I check their work.

I study computer science and math at the University of San Diego and build AI tools for my own underwater footage. GitHub counted 30,433 contributions from me in 2026, nearly all in private repos. Of the 14,493 commits on my Mac, 49.5% name Claude as a co-author.

Data as of Sun, Nov 1, 2026.

## Where the commits went

Five projects hold 23,184 of the 23,817 commits I can count this year. GitHub's 30,433 also counts pull requests, so a merged change often counts twice.

### Reef (in progress)

SwiftUI · Python · MCP. A native Mac editor that finds the moments in hours of dive footage, and lets an agent edit the same timeline I do.

- Implemented: the SwiftUI app runs over a Python engine. Agents reach it through 176 MCP tools: 96 read-only and 80 that write, each one free (145), ask first (15) or behind a hard gate (16). Every edit goes through one writer that checks the project revision first.
- In progress: no end-to-end run, from raw footage to a finished cut, has been demonstrated yet.
- Worth a look: telling the describer where a dive took place raised its accuracy from 38 to 44 of 52 hand-labelled clips (recorded Oct 5). 11,736 commits on this Mac since Jun 8, 9,919 of them on main.
- Showcase repo: https://github.com/henryhcooperr/reef
- Case study: /work/reef/

### COOPR (unfinished)

React · TypeScript · Python · MCP. A creator workspace where the conversation turns into the document. Most of my commits before Reef went here.

- Exists in source: Content Brain, the backend: audio and motion diagnostics, CUSUM and PELT change detection, and evidence retrieval with fallbacks. Reef reads it through a read-only client.
- Left unfinished: I moved on to Reef before the interface was wired to the live backend.
- Worth a look: 8,741 commits from Feb 20 to Jul 20, and a $3,000 award from the University of San Diego in 2026.
- Showcase repo: https://github.com/henryhcooperr/coopr
- Case study: /work/coopr/

### Grade Lab (in progress)

Python · DaVinci Resolve · MCP. Underwater color that remembers what I said. An agent grades my footage inside DaVinci Resolve, on real nodes I can open and keep editing.

- Works today: the agent builds each grade on a 20-node Resolve template through an MCP server I wrote, and saves every verdict I give: 133 on 26 shots so far. 21 of the 26 shots reached a grade I praised within three versions.
- In progress: replay proof is built but hasn't been exercised yet.
- Worth a look: 1,263 commits on this Mac since Sep 29. The busiest day was Oct 5.
- Showcase repo: https://github.com/henryhcooperr/grade-lab
- Case study: /work/grade-lab/

### Social Lab (in progress)

Python · Node. Finds real public posts like the dive videos I make, then asks whether each one actually beat its creator's usual.

- Works today: each post is scored against the same creator's other posts, with a robust z from the median and MAD and a seeded 2,000-draw bootstrap. It refuses to score with fewer than 10 other posts, and an evidence ladder stops an agent from claiming a level it hasn't reached. 2,928 Python and 364 Node tests passed at the Oct 28 gate.
- Worth a look: indexing 2,062 captions cost $0.0415048, exactly the quote, across 21 of 21 requests.
- Showcase repo: https://github.com/henryhcooperr/reef-social-lab
- Case study: /work/social-lab/

### Kelp forest (done)

three.js. The interactive version of this portfolio: a three.js coast and kelp forest you swim through.

- Works today: live at https://henrycooper.dev and https://henryhcooper.com. 1,815 tests, with 13 known failures tracked in a file and none new.
- Worth a look: built in seven days by agents working in parallel: 1,081 commits, 99 branches and 77 worktrees. Separate judge agents marked each change PASS, REVISE or NOT VERIFIED, and frame timings came from a real GPU on a second Mac.

### Also

- Algorithm studies (done): six pieces of math from Reef, Grade Lab and Social Lab, each a JavaScript port of the real function with its real constants, run on sample inputs. https://github.com/henryhcooperr/reef-algorithm-studies Case study: /work/algorithm-studies/
- lens (done): my footage library CLI. It backs up and organizes dive footage, and proves every copy with an md5 fingerprint. At the Oct 5 scan it held 123 trips and 3.7 TB. Case study: /work/lens/

## How I build

ChatGPT was debugging my intro CS assignments, so I put my time into AI, system design, algorithms and math instead. I added a math major and moved into ML and data science. Now I write the rules, agents write most of the code, and nothing counts until it is checked.

- Each agent gets its own worktree, instead of one shared checkout.
- A separate agent judges the work, instead of the builder's own report.
- Only my words approve, instead of a passed check counting as approval.

## Résumé

- University of San Diego: B.S. Computer Science (AI and Data Science), with a second major in Mathematics. Expected Dec 2026.
- FICO, Analytic Science Intern, May – Aug 2025.
- Fictiv, Computational Geometry Intern, Jun – Aug 2024.
- University of San Diego, Teaching Assistant, Programming Abstractions, Jan – Jun 2024.
- COOPR: $3,000 award from the University of San Diego, 2026.

## Contact

- Email: henryhcooper@gmail.com
- GitHub: https://github.com/henryhcooperr
- LinkedIn: https://www.linkedin.com/in/henryhcooper