1
Run one command
From inside your project:
init asks one question, which coding agent do you prefer, shows what it detected (Claude Code, Codex, Pi, …), and scaffolds .smithers/ with the focused authoring pack (create-workflow, create-skill, docs-driven-development), installs dependencies, and installs that agent’s plugin (or skill). Former recipes live under examples/init-pack/; piped or non-interactive callers (CI, agents, --yes) skip the question and install defaults, and --no-tutorial skips the guided session.create-workflow is the scaffold’s star: describe the workflow you want and it writes that plus a companion skill document. Re-running init later only offers to update files that drifted.2
Make sure your agent knows Smithers
Your agent drives Smithers. Two ways to give it the context it needs:
- Have your agent read the docs. Ask it to run
bunx smithers-orchestrator docs(concise index) orbunx smithers-orchestrator docs-full, or point it athttps://smithers.sh/llms-full.txt. Quick, no install. - Install the plugin or skill for your harness so context is always loaded. Each page below has the exact install:
init already installs the best integration for your preferred agent: the Claude Code plugin, the Hermes/OpenClaw native plugins, or the curated skill for Codex, Pi, OpenCode, Kimi, Amp, and Antigravity. Use the page above for your harness to wire additional agents or add MCP.3
Ask your agent to create a workflow
You don’t run Smithers, your coding agent does: you describe outcomes, it picks and runs the workflow. Ask it, in plain language:
“Use create-workflow to build a workflow that checks my API and keeps iterating until tests pass.”Your agent runs
create-workflow; a durable run completes and reports the generated workflow and companion skill path back to you.Run it yourself in a terminal and a cheap, fast model narrates the result: a short recap plus a self-contained HTML summary that opens in your browser (written under .smithers/reports/). Pass --no-report, or set SMITHERS_NO_REPORT=1, to skip it.This runs the coding agent
init detected (Claude Code, Codex, …), so have one installed and signed in.4
Ask your agent to open the run UI
To watch a run live in your browser, ask your agent:
“Open the Smithers UI for that run.”Your agent runs
bunx smithers-orchestrator ui <RUN_ID>, which opens the run’s live status card (stages, output, any approval gates) in your browser. Keep it open while you hand off more work.Read next
Your agent ran a workflow; pick what you need next.Talk to your agent
How-to: phrase requests so your agent picks the right workflow every time.
Watch and steer
How-to: follow a live run, clear approvals, and redirect without touching code.
What you can do
Reference: the catalog of outcomes you can hand off, and what to say.
The few concepts you need
Explanation: the handful of ideas behind durable runs, gates, and loops.