agents

Accept EditsAuto-accept file edits; still confirm other destructive actions.AgentA named AI agent (called a subagent by some client products) that carries its own system prompt, description, tool access, and references to the skills and…Agent IDShort machine identifier for the agent. Lowercase letters, numbers, and hyphens only. Maps to the name field in Claude Code subagent frontmatter, the name…AutoAuto-accept anything the host considers safe.Bypass PermissionsSkip all permission checks. Intended for sandboxed environments where there is nothing the agent can damage. ColorOptional display color used by clients that show running agents in their UI. Recognized values follow the Claude Code palette: red, blue, green, yellow,…DefaultConfirm destructive actions. The standard mode for interactive sessions. DescriptionHuman-readable one-line description telling the host client when to delegate to this agent. The host uses this string to decide whether an incoming task…InstructionsThe agent's system prompt in markdown. Rendered verbatim into the body of the generated Claude Code or Gemini markdown file, and into the…Max TurnsOptional. Maximum number of agentic turns the agent is allowed to take before it stops. Useful to cap runaway exploration for narrowly-scoped subagents. ModelOptional. Model alias or full model id the agent should use (e.g., "sonnet", "opus", "haiku", "claude-opus-4-6", "gpt-5", "gemini-2.5-pro"). When omitted, the…Permission ModeA named policy governing how aggressively an agent is allowed to take actions without asking for confirmation. Modeled as a class so concrete modes (default,…Permission ModeOptional. The named permission policy the host should apply when running this agent. Clients that do not support a particular mode fall back to their own…PlanRead-only planning mode. The agent gathers context and proposes a plan but cannot execute destructive actions. SpeaksProtocols the agent uses to talk to tools or other agents. Typical values point at kanonak.org/mcp for tool access and kanonak.org/a2a for agent-to-agent…Target ClientOptional. Restricts this agent to a specific client or set of clients (e.g., only claude-code because the instructions rely on a Claude Code feature). When…Uses SkillSkills this agent knows how to use. Deploying the agent to a client SHOULD transitively deploy its referenced skills, so an agent that declares a skill via…Uses ToolTools the agent is pre-approved to invoke. Matches the tools field in Claude Code subagent frontmatter. Leave empty to inherit every tool from the parent…