Codex drafts the plan next to the repo. The people who will run it comment on one link, and agent connect carries a change back into that session.
What people write with Codex
Pick a doc type to see who reviews it, and what agent connect changes.
How it works
Author writes, reviewer comments, Codex acts. The same hosted link covers the whole loop, before the file ever sees git.
Goal: stop losing carrier callbacks during peak shipping season by retrying failed webhooks with exponential backoff, with a kill switch.
1. Enable for staff accounts only. 2. 10% of production traffic. 3. 50%, then 100% if error budget holds.
Open questions: who owns the cleanup two weeks after 100%? [[anchor]]Do we keep the legacy retry path in process, and for how long?[[/anchor]]
Codex writes markdown. Gander watches.
Reviewer opens the link. No install. Inline threads on the live doc.
Agent connect reaches Codex. It edits the file. The same link refreshes.
Install
The same install works on macOS and Linux. Windows users should use WSL.
$ curl -fsSL https://release.gander.md/install.sh | bash
$ gander signup --email [email protected]
$ gander watch plan.mdOr: install the Gander skill and let the agent save the plan, watch the file, and poll for review. Skill docs.
Homebrew, flags, and other options: Install docs.
The skill loads from ~/.agents/skills. The MCP table in ~/.codex/config.toml carries agent connect into the Codex session.
Step-by-step setup: Codex docs. Every agent: Use with your agent.
Using a different agent? Other agents.
Leave a thread on the line that should change.