Protocol

Start a resumed agent session with a workspace sanity check

Before the next shift starts building, make sure the factory still turns on.

When it fits

  • A new AI session is about to continue work left by another session or worker.

When to avoid it

  • Keep the startup test proportional; an hour-long full suite can become ritual waste when a two-minute smoke test answers the baseline question.

Why it matters

Read the progress handoff, inspect recent changes and run the cheapest representative smoke test before editing. If the baseline is already broken, diagnose or record that state first. This prevents a fresh agent from building on undocumented failure and later attributing old breakage to new changes.

Steps

  1. Read the current progress or decision artifact.
  2. Inspect recent commits or changed files.
  3. Run one cheap representative smoke test.
  4. Record baseline failures before making a new change.

An example

Before modifying a web app, the agent starts the dev server and checks the primary route rather than assuming the previous session left it healthy.

Check your result

The session has an explicit known baseline before its first substantive edit.

Keep this limit in mind

  • Keep the startup test proportional; an hour-long full suite can become ritual waste when a two-minute smoke test answers the baseline question.

Connected ideas

Use before
Ask a coding agent for one coherent increment at a time

Evidence and sources

Supports

Anthropic recommends beginning resumed coding sessions by reading progress artifacts and running a basic test so undocumented breakage is discovered before new changes.

The startup check must stay cheap enough that it does not consume the work session.

Effective harnesses for long-running agents · Coding agent behavior at session start

All sources (1)