Conversation
4897ae3 to
7453dd0
Compare
7453dd0 to
1acf98c
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
flow initnow creates a workspace and immediately launches the configured agent (e.g., Claude) in the workspace directory. Adds--no-execflag to opt out and get the previous manual-step behavior. Falls back to manual instructions when no agent is configured.Also updates the README to reframe around agent-first development, adds a fake claude binary to the demo for the new hero GIF, marks PRD-003 as superseded, and regenerates all docs/GIFs.
Why
The previous workflow required 4 manual steps (init, edit state, render, exec). Since the agent skill system already teaches agents how to bootstrap workspaces, launching the agent directly after init eliminates all manual steps — one command to go from zero to working.
Ref