Drive Smithers, a durable control plane for long-running coding agents. Use when the user wants multi-step, long-running, crash-safe, or human-in-the-loop agent work: "orchestrate agents", "run a workflow", "implement this and review it", "keep iterating until tests pass", "plan then build", or anything that needs retries, approvals, replay, or evals across multiple AI steps. YOU (the agent) run Smithers on the user's behalf; it is not a GUI the human clicks. You are an ORCHESTRATOR: run long-running, multi-step, or background work *through* Smithers, not through your own ad-hoc subagents; spend your time observing the run and reporting.
The concierge proxy — turn a vague user script ("I need the agent to help me do X") into a context contract, route it to the right skills/workflows, add backpressure (tests/evals/reviews/approvals), execute, and report. Use when a request is multi-step, durable, or human-in-the-loop and you'd otherwise hand-roll the orchestration; skip it for a single prompt → single answer.
Turn acceptance criteria into a runnable Smithers eval suite (JSONL cases + rubric) and wire it to `smithers eval`. Use when a workflow's quality must be measured and regression-tested — not "looks good" once, but a repeatable check that fails when the model OR the harness regresses.
Turn a run's persisted state into a self-contained HTML slideshow report — objective, decisions, graph, gates, evals, artifacts, failures, and the recommended next run. Use when a long or important run needs a legible, shareable summary instead of scrolling raw logs.
Drive Smithers, a durable control plane for long-running coding agents. Use when the user wants multi-step, long-running, crash-safe, or human-in-the-loop agent work: "orchestrate agents", "run a workflow", "implement this and review it", "keep iterating until tests pass", "plan then build", or anything that needs retries, approvals, replay, or evals across multiple AI steps. YOU (the agent) run Smithers on the user's behalf; it is not a GUI the human clicks. You are an ORCHESTRATOR: run long-running, multi-step, or background work *through* Smithers, not through your own ad-hoc subagents; spend your time observing the run and reporting.
Drive Smithers, a durable control plane for long-running coding agents, from Claude Code. Use when the user wants multi-step, long-running, crash-safe, or human-in-the-loop agent work ('orchestrate agents', 'run a workflow', 'implement this and review it', 'keep iterating until tests pass', 'plan then build') or anything needing retries, approvals, replay, or evals across multiple AI steps. YOU (Claude) run Smithers on the user's behalf; it is not a GUI the human clicks. HARD RULE 1, run long-running / multi-step / background work through a durable Smithers workflow, NOT through Task/Agent subagents, /loop, or hand-written native Workflow scripts; the native Workflow tool has exactly ONE sanctioned use, launching the plugin's smithers-run.mjs mirror so the run shows live in /workflows. HARD RULE 2, every workflow you create or run MUST get a live custom UI at .smithers/ui/<key>.tsx (built with gateway-react) and you MUST launch it with `smithers ui` so the human can watch. HARD RULE 3, when creating or editin
Design the Zod output schema of a Smithers <Task> as the contract between steps. Use when a step's output feeds a later step (or a branch/loop condition) and must be reliable — design the schema first, keep it minimal, and prefer typed fields over prose so downstream rendering can depend on it.
Drive Smithers — a durable control plane for long-running coding agents — from inside Hermes. Use for any multi-step, long-running, crash-safe, or human-in-the-loop work: "run a workflow", "implement and review", "keep iterating until tests pass", "plan then build". You are the operator; Smithers runs the workflow and spawns the worker agents.