create-workflow to author the durable recipe you need or copies a
matching pattern from examples/init-pack/, then drives it through to a
validated result. The rows below describe those copyable patterns; they are not
installed by init.
This page is the catalog. Each row is an outcome you want, the exact words you say to your agent, and what Smithers does under the hood.
Build
You know what you want shipped. These workflows turn a request into validated, reviewed code, enforcing a build-check-review loop instead of handing you a first draft.
implement runs a build → validate → review loop and feeds failures back in, so you get reviewed code instead of a first draft.
research-plan-implement gathers context and plans before touching code, the pipeline for work in unfamiliar territory.
mission breaks long-horizon work into approved milestones with parallel workers, so a multi-day migration runs as scoped, reviewable chunks.
kanban implements each ticket in its own worktree branch and merges only the ones that pass: isolated parallelism on one board.
Plan
Shape the work before any code is written. These produce plans, tickets, and sharper requirements. Nothing touches the repo.
plan returns ordered steps without changing the repo, the input you feed into implement, mission, or tickets-create.
tickets-create splits one broad request into discrete tickets with acceptance criteria; drop them in .smithers/tickets/ and hand them to kanban.
grill-me interrogates you before any planning, so the plan is built on real requirements instead of a vague one-liner.
research gathers repo and external context up front, so the plan that follows cites real files and prior art.
Quality
Make existing work stronger: review it, fix bugs at the root, raise coverage, and audit the whole repo for gaps.
review returns approval status plus issues tagged by severity, so 'is this production-ready' gets a structured answer.
debug reproduces the bug before fixing it and runs every validation iteration, with no early exit until the fix is verified.
improve-test-coverage fills high-impact gaps and validates that the new tests actually pass.
feature-enum produces a code-backed feature inventory that audit then reviews group by group in parallel: a whole-repo gap report.
audit consumes the feature map and reviews each group for missing tests, docs, and error handling across the whole inventory.
Run while you’re away
Smithers runs are durable. They survive crashes, restarts, and flaky tools, and the runtime always knows what’s done and what’s next. So you can start something long-running, close the lid, and come back to progress. Keep going until you stop it. Say:“Keep working on reducing our flaky tests and don’t stop until I tell you to.”Your agent runs
ralph, an unbounded loop that re-runs the smart agent on your prompt. When you’ve had enough progress, tell your agent to stop it and it runs bunx smithers-orchestrator cancel RUN_ID.
ralph loops the same prompt indefinitely, so a long-grind task keeps making progress while you're away.
“Every morning, scan the repo for stale TODOs and broken doc examples and open fixes.”Your agent registers a cron schedule (
bunx smithers-orchestrator cron add) that kicks off the workflow on its own. Ask what’s scheduled and it runs bunx smithers-orchestrator cron list.
Gate on your approval. Say:
“Draft the release blog post, but don’t publish until I approve it.”The workflow durably suspends at an approval gate. Say “approve it,” your agent runs
bunx smithers-orchestrator approve, and the run resumes exactly where it left off. The work happens while you’re away; the irreversible step waits for you. This is the same gate mission uses to hold its milestone plan until you sign off.
Make your own workflows discoverable
Smithers treats having your agent author new workflows as a first-class path. Once you’ve built task-specific and project-specific workflows, say:“Write skill docs for all the Smithers workflows in this repo so any agent can find and run them.”Your agent can copy the archived
workflow-skill
example, or ask create-workflow for the same behavior. It reads local workflow
metadata and source, then writes concise agent-facing skill docs under
.smithers/skills/.
workflow-skill turns your local workflows into agent-facing skill docs, so the next agent on the repo can drive them by name without reading the source.