openrig-dev README: the context-pack step needs the daemon; agent-driven setup (#39)

The optional rig context add step comes before rig up, and without a running
daemon it stops with "Daemon not running." Say so, and say to run rig daemon
start first.

Add a short note for people who ask Claude Code to do the setup. In a test on
macOS with Claude Code 2.1.289, its default auto mode declined three steps:
cloning and building the openrig repository, adding a permission rule for
itself, and rig context add --git. The note names each one, with the label
Claude Code shows, and says what the person does instead.

Co-authored-by: OpenRig contributors <[email protected]>
This commit is contained in:
Mike SchwarzandOpenRig contributors authored and GitHub committed 2026-10-05 02:39:15 -07:00
1 parent 3275331b6d
commit 0aacdc8e62
1 file changed
+16 -1
+16 -1
View File
@@ -42,12 +42,27 @@ worktrees the seats create, too. If you skip this step, the lead adds any
missing entries when it starts.
Optional: if this repository's context pack is not installed yet, add it so the
seats can load it at start (`rig context add --help` has the options):
seats can load it at start (`rig context add --help` has the options). It needs
the OpenRig daemon running. `rig up` starts the daemon by itself, but this step
comes first, so if `rig context add` stops with "Daemon not running.", run
`rig daemon start` and then add the pack again:
```sh
rig context add --git <path-or-URL-of-your-openrig-world-clone>
```
**If you ask Claude Code to do this setup for you,** plan to run some steps
yourself. In OpenRig's test on macOS with Claude Code 2.1.289, its default auto
mode declined three of them:
- **Cloning and building the openrig repository** (`[Code from External]`).
Run the clone and the build yourself.
- **Adding a permission rule for itself** (`[Self-Modification]`). Auto mode
doesn't let Claude change its own permissions. If you want a rule, add it
yourself with `/permissions` or in `.claude/settings.local.json`.
- **`rig context add --git`** (`[Untrusted Code Integration]`), even with an
allow rule for that command. Run it yourself.
## Run it
From the root of your openrig clone, preview, then launch: