LaunchDarkly Flag Change Watchdog with Codex
Every step is an API read followed by one small write to Slack: pull the audit entry, pull the flag, pull its status, post three lines. Codex moves quickly through API plumbing and data handling, and the edges of this job are unusually clear, so the flag key, the environment and the before and after values reach the channel the way LaunchDarkly returned them.
Watch it work before it's live
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
checkout-v2-rollout
Percentage rollout moved from 25% to 100% of all contexts. Targeting rules and variations unchanged. Comment left on the change: green in staging all week, taking it to everyone before the weekend freeze.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect LaunchDarkly
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Flag policy
Which flag changes you want to hear about and which are routine - the environments you protect, your kill switches and permanent flags, and what makes a change risky enough that a named person should confirm it.
Runs on Codex
Preselected for this page — connect your Codex account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Why Codex for this agent
Before and after, intact
A change is two values that have to survive the trip into Slack unaltered. Moving structured fields around without smoothing them is this harness at its most ordinary.
One entry in, four lines out
The task ends the moment the message posts, with no follow-up and no state carried forward. Well-scoped jobs with a visible finish are where Codex is fastest.
Before you fork
Which OpenAI sign-in should we use here?
Either a ChatGPT plan or an API key works, since Codex signs in with your own OpenAI account. The thing to check on an API key is the model, because tool exposure for connected apps follows the Codex model family and a general-purpose model can end up with no LaunchDarkly access at all. Watch the first change come through and confirm the audit lookup really ran.
Run it with a different agent
Put LaunchDarkly Flag Change Watchdog to work on Codex
Free to start. Guided setup, a test run against staged conversations, and it's live.