Skip to main content
The Endor Labs Agent Kit installs into Gemini CLI as an extension, adding the Endor Labs setup skill, workflow skills, and preview subagents.
1

Install the extension

Clone the public distribution repository, then install the generated Gemini extension from it.
git clone https://github.com/endorlabs/ai-plugins
gemini extensions install ./ai-plugins/plugins/gemini/endor-labs-agent-kit
gemini extensions list
Gemini CLI may show a folder trust prompt for local paths. Inspect the package and approve only the expected Endor Labs Agent Kit extension source. Restart Gemini CLI after installing or reinstalling the extension.
Google documents Antigravity CLI as the consumer transition path for Gemini CLI. If your Gemini CLI account is affected by that transition, use the Antigravity CLI package instead. Keep this Gemini extension for supported Gemini CLI environments.
2

Set up this machine

Ask your AI coding assistant to run the setup skill.
Use the endor-agent-kit-setup skill to check Endor Labs Agent Kit readiness.
The setup skill guides package-manager-first endorctl installation, verifies Endor Labs authentication and namespace readiness, and reports missing gh or toolchain prerequisites. It does not run scans, run endorctl host-check, edit shell profiles, auto-install gh, or install language runtimes and package managers.
3

Run your first workflow

Each workflow is available as a skill and as a subagent. Invoke a subagent with @<name>. Try these example prompts.
@ai-sast-triage triage AI SAST findings for this repository

@sca-remediation check this repository for P0 SCA findings I can start remediating

@probe-droid probe GitHub org <org> for Endor Labs monitored-branch onboarding gaps and setup prescriptions

@endor-troubleshooter diagnose this Endor Labs scan failure from redacted error text and read-only tenant evidence
See the Agent Kit overview for the full agent catalog, and the safety model for how mutating agents handle approval gates.