Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull requests, or human-owned task systems and cannot rely on an in-run subagent result.
Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify repository state outside the coordinator's worktree.
Design framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents, OpenAI Agents SDK services, LangGraph graphs, Hermes-specific workflows, full-auto execution, auto-with-escalation, or no automation yet, and when the user wants…
Design evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds, regression runs, full-auto gates, or escalation points for Codex skills, repo-local agents, OpenAI Agents SDK services, LangGraph graphs, or other agentic workflows.
Coordinate bounded worker tasks with a launch envelope, report-back, escalation, and synthesis contract. Use before spawning, resuming, steering, cancelling, or closing subagents.
Choose and design one-shot, recurring, event-triggered, monitored, CI, background, queue, or board-based agent work. Use when agent work must run later, repeat, survive the current thread, or deliver results through an explicit route.
Create or align agent plugin repositories, install deterministic managed FSX plugin maintenance, and validate or apply the whole plugin set through exactly two aggregate Just commands.
Design, implement, test, and package an ACP agent/server. Use for protocol negotiation, sessions, streaming updates, tool rendering, permissions, authentication, SDK choice, and registry submission.
Choose A2A, ACP, MCP, a native host integration, a terminal thread, or a Hermes programmatic interface. Use when the direction of agent, editor, tool, or host control is unclear.
Route Hermes Agent work to the correct operator, extension-development, messaging-gateway, Nous services, or Socket compatibility workflow. Use when a request spans surfaces or its extension boundary is unclear.
Connect, expose, validate, and troubleshoot Agent2Agent (A2A) peers. Use for Agent Cards, peer authentication, message and task lifecycles, streaming, push notifications, or Hermes A2A across process, machine, or framework boundaries.
Install, launch, validate, and diagnose existing ACP agents across Zed, Xcode, and other clients. Use for registry discovery, custom launch commands, auth, capabilities, sessions, and logs.
Configure, run, secure, and troubleshoot Hermes Agent messaging gateways, platform adapters, webhooks, API server, long-lived profiles, and remote deployments across built-in and custom channels.
Configure and troubleshoot Zed Agent, ACP External Agents, and Terminal Threads. Use for Zed Skills, MCP, profiles, permissions, registry installs, custom agents, and ACP logs.
Use and troubleshoot Nous Research services with Hermes Agent, including Nous Portal inference, Tool Gateway backends, Nous Chat, subscription proxy, and Hermes Cloud hosted deployment.
Choose the right Android project, app, library, module, language, UI, build, test, lint, signing, release, or dependency-maintenance shape before implementation. Use when Android work needs routing across Kotlin, Java, Gradle, Android Gradle Plugin, Compose, XML views, emulator-aware validation, release readiness, or…
Maintain Java-only Android projects and Kotlin/Java interoperability inside Android apps or libraries, including Java source sets, AndroidX Java APIs, annotations, nullability, SAM boundaries, generated bytecode expectations, public API compatibility, tests, lint, and migration guardrails.