Implement the session-start protocol

Orientation before action, every single time.

First time here? Paste the Context Pack first so the AI understands your project - open it from the header above.

Prompt Capsule

Build the session-start protocol. On starting a session in the project: (1) load PROJECT_STATE.md into context under an orientation header; (2) run drift checks - verify done-milestone evidence still holds (files exist, tests still pass if cheap to run) and the workspace map matches reality; (3) render an orientation summary: goal, position, next action, open blockers, plus any drift warnings; (4) the agent's first output confirms its understanding of the position and proposes to proceed with the recorded next action (or flags why not). Test by starting a session and checking the orientation against the document by hand.

Paste into EmergentFull Build: complete implementation prompt with explicit requirements

Quick is short. Full Build is recommended for most steps. Strict forces real logic when the AI keeps faking output.

Actual change check

Expected after this step

Sessions that begin oriented, drift-checked, and pointed at the next action.

Should NOT happen

An existing feature broke
A button only logs to console
Data disappears after refresh
Errors fail silently with no visible state

This is what should exist before you continue. If reality does not match, do not move on.

Your notes for this step

Track what changed, failed, or needs follow-up. Notes export with the flow.

Pass the Verify Gate to complete this step

Verify before continuing

Do not move on until every check is true. The complete button stays locked until then.

State loaded before any task workDrift checks run with warnings surfacedFirst output confirms position and next action

Do not continue if…

! Plans living in chat history, evaporating at session end
! State documents that describe the past but not the current position and next action
! Sessions editing state destructively so history and rationale vanish
! State drifting from code reality until it misleads instead of orients

If the AI messes this up

Use this when:

- it only made visual forms or placeholder UI
- buttons do nothing or only log to console
- data is not persisted - state disappears on refresh
- something that worked before is now broken

Use this when the AI fakes progress or breaks the feature. It forces a real fix.

The agent acknowledges the state then ignores it. Make the next action binding: the system prompt instructs that deviation from the recorded next action requires stating a reason that gets logged to the changelog.