Hal turns product requirements into bounded stories, runs them through Codex, Claude Code, or Pi, and leaves reviewable commits, reports, and state before you merge.
Proof you can inspect before you run it
Hal wraps AI coding agents in a loop that plans scope, bounds context, preserves state, and keeps the human in review.
Turn product intent into stories and acceptance criteria before an agent touches the repo.
Give each implementation story its own context so long features do not become one drifting chat.
Use Codex, Claude Code, or Pi inside the same PRD-driven workflow and review process.
Carry repo commands, conventions, and review rules into each implementation loop.
Keep progress, reports, workflow files, and archives available for inspection or later continuation.
Move through plan, convert, validate, run, report, and archive behavior as explicit steps.
Use Hal when the task is clear enough to plan, risky enough to review, and repetitive enough to deserve a loop.
One explicit pipeline from product intent to reviewable changes.
Run hal plan and describe the feature. Hal asks clarifying questions, then generates a structured PRD.
hal convert transforms the markdown PRD into structured JSON. The runtime state is ready.
hal validate checks every story against quality rules. Broken PRDs never enter the loop.
hal run picks the next story, runs implementation, commits reviewable state, and repeats through the planned work.
Hal supplies the loop. Codex, Claude Code, or Pi supplies the implementation engine.
Install Hal, start with a bounded requirement, and inspect the resulting commits before merging.