Prepared reference; not released. Exact source.
Prepared reference only; not a public release.
agentplugins author
Build Agent Plugins packages
Synopsis
Build Agent Plugins packages.
Inherited --scope, --accept-security-risk, and --security-details are installer-only and rejected here. Select the package with the positional path; use author doctor for project diagnostics. Use agentplugins add for installation/security policy.
Options
-h, --help help for authorOptions inherited from parent commands
--accept-security-risk continue despite blocking automated security findings
--dry-run show the exact plan without changes
--format string output format: human or json (default "human")
--no-color disable color output
--scope string installation scope (user only in this release) (default "user")
--security-details show every automated security finding in human output
--target string target client(s), comma-separated: codex, chatgpt, cursor, copilot, vscode, kiro, claude, gemini, opencode, cline, windsurfSEE ALSO
- agentplugins - Install and manage Agent Plugins 1.0 packages across AI clients
- agentplugins author capabilities - Show embedded schemas, profiles, live client metadata and implemented commands
- agentplugins author compat - Evaluate explicit --target clients using static adapter support; no installed clients required
- agentplugins author doctor - Inspect captured native files and executable metadata; no processes or network
- agentplugins author init - Create an offline standard package in an absent destination
- agentplugins author inspect - Inspect captured components and unresolved runtime requirements
- agentplugins author skills - Create and validate standard package Skills
- agentplugins author test - Check configuration, hygiene, Skills and MCP statically; runtime is not evaluated
- agentplugins author validate - Validate exact-root standard configuration and authoring readiness
- agentplugins author version - Print product version and shared authoring engine revision