The marker is committed, so M1's own agent reads it too. The first version told whichever side read it to run m1-say — on M1 that meant relaying to itself. Now each side is told its role by a one-line check for the M1-only token file.
22 lines
1.1 KiB
Markdown
22 lines
1.1 KiB
Markdown
|
|
## This project lives on M1
|
|
|
|
All coding, browsing, testing and compiling for this project happens on the
|
|
always-on **M1** server. First find out which side you are on — run once:
|
|
`test -f ~/.config/claude-m1.env && echo "I am M1" || echo "I am the M5"`.
|
|
|
|
**On M1 — you are the worker.** Work normally in this repo: read, edit, build,
|
|
test and commit here. Ignore the relay notes below; they are for the other Mac.
|
|
|
|
**On the M5 — this folder is a read-only git mirror.** Do not edit files here
|
|
and do not run builds or tests here.
|
|
|
|
- For **every** message about this project, run `m1-say "<the message>"` and
|
|
show M1's reply. M1's agent does the work, on M1, and keeps going even when
|
|
this Mac sleeps. You are the pipe. (Questions about the relay itself you may
|
|
answer locally.)
|
|
- To refresh this mirror with M1's latest work: `m1-back` — a git merge, never
|
|
rsync, never an overwrite. Then `git log` / `git status` show what changed.
|
|
- M1 is the git remote `m1`. If something truly must be committed from here,
|
|
push it with `git push m1 main` — but prefer telling M1 to do it.
|