A runtime that runs the work around AI-written code for you: picking tasks, managing branches, reviewing code, cleaning up artifacts, handling CI and PR comments, and deploying. Pipelines pause at gates and keep state across sessions.
@agent-shGives AI agents control of a Linux desktop through accessibility trees, screenshots, window targeting, and synthesized click, type, and scroll input. Works through MCP, Pi tools, or a CLI.
@agent-shLints and validates AI coding assistant configuration files such as CLAUDE.md, AGENTS.md, SKILL.md, hooks and MCP setups, with autofixes and editor integration for common IDEs.
@agent-shUse when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent…
@agent-shLinux desktop observation and control via native Pi tools or the computer-use-linux MCP server: accessibility trees, screenshots,…
@agent-shUse when preparing an AgentSys release, checking cross-platform compatibility, or changing the installer, transforms, adapters or…
@agent-shLint agent configurations with the agnix CLI and return the validation results as an AGNIX_RESULT block. Used by /agnix.
@agent-shIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
