LaunchDarkly Flag Change Watchdog with Claude Code
The workload here is one audit entry at a time, and most entries are not flag changes at all. Claude Code is the harness that reads everything available before it acts, which is the order this needs: open the entry, fetch the flag and its status, take the environment key off the record, and only then decide whether three lines or four go to Slack. The reading is nearly the whole job, since the writing stops at one short message.
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 Claude Code
Preselected for this page — connect your Claude Code 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 Claude Code for this agent
Status read before the verdict
The rollout split, the variations and where the flag is still evaluated have to be read first, or the why-it-matters line means nothing. Gathering first is how this harness works anyway.
Two shapes, chosen carefully
Three lines is routine and four lines names a person who should confirm. Choosing between them on your written policy rather than on how alarming the diff looks is judgement, not formatting.
Before you fork
Does it need a writer token to do this properly?
No. A read-only LaunchDarkly token covers flags, flag status and the audit log, which is the whole of what it touches. Granting a writer role would let it toggle the flag it is describing, and no part of the template would ever call that.
Run it with a different agent
Put LaunchDarkly Flag Change Watchdog to work on Claude Code
Free to start. Guided setup, a test run against staged conversations, and it's live.