Configs Targeting

This handles the targeting side of LaunchDarkly's AI configs, letting you set up rules for who gets which model configuration. You can do percentage rollouts, attribute-based targeting, segment rules, and individual overrides. The workflow is get current targeting to grab variation UUIDs, then send semantic patch instructions to add rules or update the fallthrough. One gotcha worth knowing: the usual turnTargetingOn instruction doesn't work for configs, you have to use updateFallthroughVariationOrRollout instead. The Python implementation shows the pattern pretty clearly. Useful if you're running controlled experiments with different model settings or rolling out prompt changes gradually.

skills.sh installs: 1.3K
GitHub stars: 19
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add launchdarkly/agent-skills --skill configs-targeting --agent claude-code

Installs into .claude/skills of the current project.

Files

Config Targeting

Configure targeting rules for configs to control which variations serve to different contexts. Works the same for both completion and agent mode.

Prerequisites

LaunchDarkly account with AgentControl enabled
Project key and environment key
Existing config with variations (use configs-create skill)

API Access

Use the LaunchDarkly MCP server tools: they authenticate via OAuth and need no token. The REST examples under Scripting without MCP are for code that runs without the agent; if the user wants one run in this session, ask them to paste an API access token and substitute it for {api_token}. Do not search environment variables, .env files, or agent/MCP config files for credentials.