Configured Agent for Claude Code

Configured Agent is Skill Road's unambiguous mapping of the Smithery slug configured-agent to Anthropic's official plugin-settings path in the claude-code repository. The catalog name follows the registry label, while the first-party source defines the technical identity. Anthropic documents a pattern there for Claude Code plugins that need project-specific settings and state stored in a file under .claude. The file uses the plugin name with a .local.md suffix, YAML frontmatter for structured values, and an optional Markdown body for additional context. This entry is therefore classified as a skill rather than a standalone agent, server, or executable plugin.

Purpose and scope

The pattern is intended for plugin maintainers, developers, and teams that need plugin behavior to be configurable per project. According to the provider, hooks, commands, and agents can read the file and consume expected configuration values. A missing document is a normal state. A plugin can then use safe defaults or skip an optional feature. This separation keeps shared plugin logic distinct from local preferences and prevents one workstation's state from silently becoming a team convention. The skill documents a file pattern; it does not install an extension and it does not grant additional permissions.

Structure and operation

Anthropic describes YAML frontmatter between two delimiter lines and a Markdown section for notes, task descriptions, or supporting context. Configuration may contain activation flags, modes, numbers, strings, and simple lists. A responsible implementation first checks whether the file exists, accepts only a defined schema, and validates every value before using it. Boolean values should be compared strictly, numeric values need meaningful bounds, and paths must be protected against unexpected targets and traversal. Successfully reading a file is not the same as approving a hook or script for execution.

Lifecycle and team boundaries

The file is designed for one project and local customization. According to the provider, it should normally stay out of Git, and matching .gitignore rules help prevent accidental sharing. Claude Code must be restarted after a settings change so hooks recognize the new configuration. The skill recommends using the CLAUDE_PLUGIN_ROOT variable for plugin-owned resources instead of hardcoded paths. Teams should document the schema, defaults, allowed values, runtime dependencies, and restart behavior in the plugin. Shared standards belong in versioned plugin files, not in local state files.

Security and limitations

Settings files are inputs and may contain sensitive or ambiguous content. Secrets, tokens, and credentials do not belong in this file. Before activation, review hooks, shell scripts, network access, write operations, and environment variables separately. The frontmatter format grants no permissions and proves no trustworthiness. It also does not replace centralized secret management, code review, or defenses against prompt injection. Skill Road lists this as an external, verified Anthropic skill according to the provider sources and states no concrete prices. Check current Claude Code availability and terms for connected services with the provider.