# How Chris McCord actually uses coding agents

Creator of Phoenix, Phoenix.new

**If you take one thing:** ``notify msg``, in CLAUDE.md, not a hook. instead of hooks, one line in his global CLAUDE.md makes Claude ping him when work is done.

- **Agent:** Claude Code ([source, 2026-01-28](https://x.com/chris_mccord/status/2016576023400181773))
- **Model:** Claude ([source, 2026-01-28](https://x.com/chris_mccord/status/2016554559078883510))
- **Review:** Rules file names the tests to run before claiming a fix ([source, 2026-09-09](https://github.com/chrismccord/ekv/blob/becf31e79cbf923c33d4858b6f04ab077f27a5d7/CLAUDE.md#L508-L520))
- **Harness:** One continuous Claude session per project, auto-compact, rare forks, no subagents ([source, 2026-01-28](https://x.com/chris_mccord/status/2016554559078883510))
- **Rules file:** Global ~/.claude/CLAUDE.md (private) plus a per-repo CLAUDE.md (520 lines in ekv) ([source, 2026-09-09](https://github.com/chrismccord/ekv/blob/becf31e79cbf923c33d4858b6f04ab077f27a5d7/CLAUDE.md#L3-L4))

## In their words

> it still runs precommit for me just fine. I think skills and hooks make sense, but a root ~/.claude/CLAUDE.md with what it should do, and what it should call , ie when it's done work it runs a `notify msg` bash function I have, has been enough for these things.

> Meanwhile I run one continuous claude convo per project, with the very rare fork.

> Add or update adversarial/distributed tests for every safety bug fix.

> I've never used a subagent. Never used MCP. I let it auto compact and continue as necessary.

> This file is for AI agents working on EKV from a cold start.
It is not user-facing documentation.


Archetype (our label): Purist. Newest source: 2026-09-09.
Card: https://www.prehistoriq.com/stacks/chrismccord/ · Data: https://github.com/prehistoriq/stacks/blob/main/data/stacks/chrismccord.json