join-talk

1# join-talk
2 
3Needs: tmux (or the optional Orca app) as the terminal, or a Cursor IDE chat, `jq`, `flock`, and the `sno` CLI with its Reach runtime.
4Reach is the messaging layer between agents (see the `reach` skill): a seat is one registered terminal with an
5address, a card is a stored message, and a ring is the wake-up that asks the agent to read its inbox.
6`SNO_EXECUTOR_ADDR` is the environment variable holding that address for agents opened through Reach; a
7manually opened agent has none, which is what this skill fixes.
8 
9Run this once, from your own shell tool, in the repository you are working on. The script
10ships beside this file:
11 
12```bash
13bash scripts/join-talk.sh
14```
15 
16(Give the full path of this skill's `scripts/join-talk.sh` under whichever skills root your
17harness loaded it from.)
18 
19It prints one line, `joined <address>`. Tell the person that exact address, then go back
20to what you were doing. Rerunning it from the same terminal changes nothing. The seat is
21registered wherever agents on this machine are addressed, so cards, rings and a handoff find
22this terminal; `sno reach call` works for a tmux terminal, not for an Orca one.
23A Cursor IDE chat has no terminal: it is registered by its conversation id (channel `cursor-ide`), and a
24card reaches it when its turn ends. A Cursor CLI must run under tmux to be reachable.
25 
26Options, only when the person names them: `join-talk.sh review.example-repo@host1` picks the address;
27…