Skip to content

docs(skill): handle first-run trust prompt after agent start #2408

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
MarcusNeufeldt wants to merge 1 commit into from
+10 −0
Closed

docs(skill): handle first-run trust prompt after agent start #2408

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions skills/herdr/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -119,6 +119,16 @@ herdr agent start reviewer --kind codex --pane <returned-pane-id> -- <agent-args

`agent start` returns only after Herdr detects the expected agent in the same pane and considers it ready for interactive input. It defaults to a 30-second startup timeout.

A freshly launched agent may pause on a first-run prompt before it accepts input. In an untrusted directory, Codex asks "Do you trust the contents of this directory?" and waits for Enter; other agents may show onboarding or login screens. If the agent is not yet promptable, read the pane and answer the prompt:

```bash
herdr agent read <name> --source recent-unwrapped --lines 60
herdr agent send-keys <name> enter
```

Answer "Yes, continue" for the directory trust check only when the user has asked for work in that directory; otherwise stop and ask. After answering a first-run prompt, confirm the agent is idle before sending work.


Submit work through the agent surface:

```bash
Expand Down
Loading