What belongs in project standards?
Include build and test commands, architecture rules, code style, forbidden patterns, review expectations, and repo-specific conventions the agent should follow.
Feature 04
Give each AI coding iteration the repo-specific commands, conventions, and review rules it needs to stay consistent.
Why it matters
Agents default to generic patterns unless the repo tells them otherwise. Hal helps carry project standards into each story so implementation starts with local rules, not guesses.
Project standards are repo-specific rules, commands, conventions, and review expectations that an AI coding agent should follow during implementation. In Hal, standards help each story start with local context such as package manager, test command, architecture rules, and forbidden patterns.
Agents can write plausible code that does not match the repo. They may choose the wrong package manager, miss the test command, invent folder patterns, or use a style the team already rejected.
Those mistakes are not always model failures. Often, the agent simply did not receive the local rules.
Hal includes project standards as part of the loop context so each story starts with the commands, conventions, and constraints that matter for this repo.
hal init
hal validate
hal run
The point is to make the expected way of working explicit before implementation begins.
Ask whether each rule changes agent behavior. “Use our existing patterns” is weak. “Use Bun commands, keep Astro content pages in src/content, and run bun run build before finishing” is stronger.
| Hal does | Hal does not do |
|---|---|
| Structures PRD-native coding loops around planning, validation, implementation, reporting, and reviewable state. | Guarantee code quality, passing tests, delivery speed, revenue, rankings, or production readiness. |
| Helps supported engines work against smaller, reviewable units of work. | Replace developer review, QA, security review, or merge judgment. |
Before adopting this workflow, verify the current Hal source repository, install docs, pricing status, and machine-readable pricing. Check release notes and engine support before relying on Hal in production work.
Short answers before you put this into an agent workflow.
Include build and test commands, architecture rules, code style, forbidden patterns, review expectations, and repo-specific conventions the agent should follow.
Usually no. Short, concrete instructions are easier to maintain and easier for agents to follow. Add detail when repeated review feedback shows a missing rule.
No. Standards reduce avoidable mistakes, but a developer should still inspect the generated changes before merging.
Keep exploring the pieces of a reviewable coding loop.
Keep long AI coding work from turning into one drifting chat by giving each story its own bounded context window.
Use Codex, Claude Code, or Pi inside the same PRD-driven loop without rewriting your planning workflow.
Turn product intent into stories, acceptance criteria, and reviewable state before an AI coding agent touches the repo.