Skip to content

Engineering Workflows for Claude Code

Install one plugin. Get 7 specialist agents, the orchestrator methodology, global rules, and fein/sonar/blitz workflow commands.

@maestria/claude-code is a declarative Claude Code plugin: a .claude-plugin/plugin.json manifest, a directory of agent files, two skills, and three workflow commands. The agent files, skills, and workflow commands are generated from the canonical directives in packages/core/agent-directives/; the plugin manifest is maintained separately in the package.

Status: Native candidate. The plugin validates cleanly with the official CLI (claude plugin validate --strict) and follows the current documented plugin contract, but runtime behavior is not yet tested end to end. Upstream Claude Code docs are moving and unpinned - reverify before relying on any claim. Do not treat this package as a production support promise. See the runtime support matrix for evidence.

  1. Plugin loads - Claude Code discovers the .claude-plugin/plugin.json manifest and the agents/, skills/, and commands/ directories from the plugin directory
  2. Rules preloaded - every specialist agent preloads the maestria:global-rules skill via the agent skills frontmatter field
  3. Agents available - 7 specialist agents are available as namespaced @maestria:<agent> mentions
  4. Orchestrate - the /maestria:orchestrator skill routes work to specialists; /maestria:fein, /maestria:sonar, and /maestria:blitz select the pipeline depth
  5. Read-only roles enforced - adventurer, planner, and reviewer deny the Write and Edit tools via disallowedTools (user-authorized; the only runtime enforcement in the package)

The plugin is a self-contained directory. Validate it from a checkout, or install the published package persistently through the Maestria CLI:

Terminal window
claude plugin validate ./packages/claude-code --strict
claude --plugin-dir ./packages/claude-code
Terminal window
npx maestria install claude-code

Full Installation Guide →