Continue
Open source AI code assistant for VS Code, JetBrains IDEs, and Neovim.
ContinueHow skills run on Continue
Continue adds chat, inline completion, and an agent mode that makes multi-file edits from inside the editor. Its agent mode acts on repository files, so a skill pulled from a public registry can direct changes a reviewer never sees proposed.
Skill security, assessed
Every public skill in our index is assessed by the Anomity Skill Intelligence engine against its real source: remote code execution, credential and data exfiltration, prompt injection, and unsafe installers.
Govern the skill layer on Continue
Scanning a skill before use tells you what it claims to do. Anomity's Endpoint Sensor sees what agents actually do at runtime: it discovers every skill, agent, and MCP server on the endpoint, and policy can allow, deny, or log the tool calls a skill triggers on Continue and every other agent. Violations route to your SIEM, Slack, email, or Jira with a queryable 90-day audit trail.
Book a 30-minute demo to see your own agent and skill inventory.
