Aikido Security plugin

Aikido Security's own plugin for Claude Code. It bundles Aikido's skills with the Aikido MCP server, so your agent scans the code it writes or changes for vulnerabilities and hardcoded secrets, fixes what it finds, and can read and triage the issues in your Aikido security feed. What its skills do - Scan: after writing or changing code, the agent scans those files with Aikido (SAST, secrets and IaC), applies Aikido's remediation and scans again to confirm the fix - Issues: list, count and summarize findings from your Aikido feed by repository, cloud, VM, container or team, filter them by type or SLA, and dig into a single issue - PR comments: read what Aikido and your CI posted on a GitHub, GitLab or Azure DevOps pull request, through the gh, glab or az CLI - Setup: signs you in to Aikido and checks the MCP server is running What the MCP server adds - Scan dependency manifests and lockfiles for vulnerable, outdated or malicious packages - Ignore, snooze or change the severity of an issue, with a reason - Not every tool is on by default: Aikido admins choose which ones everyone gets How to install it In Claude Code, run /plugin install aikido@claude-plugins-official, then /reload-plugins, and restart Claude Code to load the skills. Then run /aikido:setup, which opens a browser window to sign in to Aikido and stores the token in your Claude Code settings. The bundled MCP server runs locally with npx and needs Node.js 18.19.0 or later. For CI or headless setups, Aikido documents token authentication instead. Good to know - Aikido doesn't decide when to scan; your agent does. You can tell it to pause scans, or to run one scan before you commit. - You need an Aikido account to sign in.