Skip to main content
context-engineer is an archived, copyable concierge example, not installed by init. Copy it from examples/init-pack/ with its dependency closure, or ask create-workflow to author a repo-specific equivalent. Hand it a vague, plain-English script and it does the context engineering for you end to end: classify, draft a context contract, grill you on blocking ambiguities one question at a time, route and gate the work, execute (or dispatch) it, and write a self-contained HTML report of the whole run.
By default it pauses for contract approval before any work executes. Clear the gate with bunx smithers-orchestrator approve RUN_ID --node approve-contract, or run autonomously with --input '{"review":false}'.

​
Stages

  1. classify-script: read the script; decide the task modes touched and whether it needs durable execution.
  2. inventory-context: inspect the repo, tools, and .smithers/skills to draft a context contract (goal, non-goals, assumptions, inputs, missing inputs, constraints, risks, desired artifacts, success criteria, verification signals).
  3. grill: resolve blocking ambiguity with GrillMe, one question at a time, each with a recommended answer.
  4. route: choose how to carry out the work: single task, skills, durable seeded workflow, or a human.
  5. build-backpressure: map every success criterion to a verification method and enforcement gate.
  6. approve-contract: durable human approval gate for the whole contract (skippable via review: false).
  7. execute: a Ralph loop that does or dispatches the work, honoring the gates, until it reports done.
  8. report: a concise HTML slideshow of the script, contract, decisions, route, gates, artifacts, and unresolved items.

​
Inputs

​
Monitor it

Use this when you have a fuzzy ask and want Smithers to do the context engineering first, instead of firing a half-specified task at a bare agent.