Virtual Icechunk · IOOS Hackathon 2026
Brainstorming, planning and directing; less coding
A short file in the repo, agent/handoff.md: where things stand.
What’s in it
How the agent uses it
The repo’s standing instructions for any agent: read at every session start.
What’s usually in it
How mine differ
CLAUDE.md is one line, @AGENTS.md. Claude Code reads only CLAUDE.md; other agents read AGENTS.md. One source, no copies to drift apart.
Markdown notes in docs/design/: the decisions, and why, with the evidence.
What’s in them
Why I do this
Bridgeford, Campbell, Chen, Lin, Ritz, Vandekerckhove and Poldrack, arXiv 2510.22254 (2025)
| Rule | In my setup |
|---|---|
| 1 · 4 Domain, solution first | A research note before any code; skills bring the domain knowledge |
| 2 Framing apart | Issues and design notes; I decide, the agent drafts options |
| 5 · 8 Context, restart | Handoff, memory, one task per session, /clear |
| 6 · 7 Tests | “Done when” on every issue; tests against the real thing; clean venv |
| 10 Small steps | One issue, one branch, one PR |
| Sandbox, approvals | Hooks block destructive git and pushes to main |
Eight of ten match. I differ on 3 and 9: I stay close to the decisions and the evidence, not to every line of code.
236 commits · ~129 issues and PRs · 1 month
Understand the design and the evidence everywhere. Read the code where the science or the risk lives.
/clearShen and Tamkin, How AI assistance impacts the formation of coding skills, arXiv 2601.20245 (2026)
Big chunks of unstructured work are how you end up not knowing what the agent did.
sudomainAgents let us build better, more reproducible code bases than most of us could write alone. To get that, adopt structured work practices and be the project manager.
⌂ Home · Working with an agent