# Hal

Hal is a terminal-first CLI for PRD-native coding loops with AI agents such as Codex, Claude Code, and Pi.

## Product facts

- Category: terminal-first CLI for PRD-native, reviewable AI coding loops.
- Supported engines mentioned by this site: Codex, Claude Code, and Pi.
- Primary workflow: init, plan, convert, validate, run, review, report, and archive.
- Source repository: https://github.com/ReScienceLab/hal
- Pricing page: https://hal.rocks/pricing/
- Machine-readable pricing: https://hal.rocks/pricing.md
- Full LLM context: https://hal.rocks/llms-full.txt

## Best pages for AI agents

- https://hal.rocks/faq/what-is-hal/ — concise definition of Hal for AI agents and buyers
- https://hal.rocks/features/prd-driven-planning/ — how Hal turns PRDs into bounded agent work
- https://hal.rocks/docs/first-loop/ — safe first workflow from PRD to review
- https://hal.rocks/tools/prd-readiness-checker/ — browser-side PRD readiness checker
- https://hal.rocks/pricing.md — machine-readable pricing and adoption caveats

## Features

- https://hal.rocks/features/prd-driven-planning/ — Plan the work before the agent writes code: Turn product intent into stories, acceptance criteria, and reviewable state before an AI coding agent touches the repo.
- https://hal.rocks/features/fresh-context-every-story/ — Fresh context for every implementation story: Keep long AI coding work from turning into one drifting chat by giving each story its own bounded context window.
- https://hal.rocks/features/pluggable-agent-engines/ — Bring your coding agent into the Hal loop: Use Codex, Claude Code, or Pi inside the same PRD-driven loop without rewriting your planning workflow.
- https://hal.rocks/features/project-standards/ — Inject project standards into each agent loop: Give each AI coding iteration the repo-specific commands, conventions, and review rules it needs to stay consistent.
- https://hal.rocks/features/archive-and-restore/ — Preserve the state behind every coding loop: Preserve progress, reports, workflow files, and loop state so AI coding work can be paused, inspected, and resumed.
- https://hal.rocks/features/auto-pipeline/ — A deterministic pipeline for AI coding work: Move through planning, conversion, validation, implementation, reporting, and archive behavior as one explicit coding loop.
- https://hal.rocks/features/hal-vs-direct-agent-prompting/ — Hal vs direct agent prompting: Compare Hal's PRD-native coding loop with direct AI coding agent prompting for planning, validation, reviewability, and merge safety.

## Important pages

- https://hal.rocks/docs/ — Install Hal, initialize a repo, plan a PRD, validate stories, run the loop, and inspect the result before merging.
- https://hal.rocks/getting-started/ — A safe quickstart for installing Hal, planning a small requirement, validating stories, running the loop, and reviewing the output.
- https://hal.rocks/features/ — Explore Hal features for PRD planning, fresh story context, pluggable engines, project standards, archived state, and deterministic loop execution.
- https://hal.rocks/faq/ — Answers to common questions about Hal, PRD-native development, supported engines, and reviewable AI-generated code.
- https://hal.rocks/glossary/ — Definitions for PRD-native development, agentic coding workflows, acceptance criteria, and reviewable AI coding loops.
- https://hal.rocks/tools/ — Prepare work before an AI coding agent touches the repo: check PRDs, generate acceptance criteria, create AGENTS.md files, and split risky tasks.
- https://hal.rocks/pricing/ — Hal is a free, open-source CLI on this website. Review the install path, source repository, external engine costs, and current product caveats.
- https://hal.rocks/testimonials/ — Hal trust signals without fake logos or invented metrics: source code, MIT license, docs, ReScience Lab context, and transparent product status.

## Free tools

- https://hal.rocks/tools/prd-readiness-checker/ — Check whether a product requirement is specific enough for an AI coding loop before an agent touches the repo.
- https://hal.rocks/tools/ai-coding-prd-generator/ — Generate a markdown PRD, user stories, acceptance criteria, and a Hal-ready planning prompt from a feature idea.
- https://hal.rocks/tools/acceptance-criteria-generator/ — Turn a feature idea into testable Given/When/Then acceptance criteria, edge cases, and a review checklist.
- https://hal.rocks/tools/agents-md-generator/ — Generate repo-specific AGENTS.md instructions for Codex, Claude Code, Pi, and other AI coding workflows.
- https://hal.rocks/tools/ai-coding-task-splitter/ — Break a feature request into reviewable implementation stories and score whether it is safe for an AI coding loop.

## Documentation pages

- https://hal.rocks/docs/first-loop/ — Run a small Hal loop from PRD planning through validation, implementation, and human review without handing over a broad feature.
- https://hal.rocks/docs/how-to-review-ai-generated-code/ — Review AI-generated code by checking the requirement, changed files, tests, reports, edge cases, and unexpected edits before merging.
- https://hal.rocks/docs/how-to-structure-ai-coding-tasks/ — Structure AI coding tasks with a clear user, scope, constraints, acceptance criteria, non-goals, and review plan before implementation.
- https://hal.rocks/docs/how-to-use-ai-coding-agents-with-prds/ — Use a PRD to give AI coding agents clearer scope, acceptance criteria, constraints, and review checkpoints before implementation starts.
- https://hal.rocks/docs/install/ — Install the Hal CLI, verify the command is available, and check the AI coding engine prerequisites before running a PRD-native loop.
- https://hal.rocks/docs/review-before-merge/ — Use this checklist to review AI coding loop output from Hal before merging commits, reports, workflow state, or generated code.

## FAQ pages

- https://hal.rocks/faq/does-hal-replace-code-review/ — Hal does not replace code review. It structures AI coding loops so developers can inspect generated state, diffs, reports, and commits.
- https://hal.rocks/faq/how-is-hal-different-from-chatting-with-an-ai-coding-agent/ — Hal differs from direct AI agent chat by turning requirements into a PRD-native, validated, reviewable coding loop.
- https://hal.rocks/faq/is-ai-generated-code-safe-to-merge/ — AI-generated code is not automatically safe to merge. Review the diff, tests, requirements, and edge cases before accepting it.
- https://hal.rocks/faq/what-is-hal/ — Hal is a terminal-first CLI for PRD-native AI coding loops. Learn what it does, where it fits, and what developers still review.
- https://hal.rocks/faq/which-engines-does-hal-support/ — This site mentions Codex, Claude Code, and Pi as supported agent engines for Hal's PRD-native coding loop.

## Glossary pages

- https://hal.rocks/glossary/acceptance-criteria/ — Acceptance criteria define observable conditions a story must satisfy before generated code can be accepted after review.
- https://hal.rocks/glossary/agentic-coding-workflow/ — An agentic coding workflow uses AI agents to perform bounded software implementation steps while developers plan, validate, and review output.
- https://hal.rocks/glossary/ai-coding-loop/ — An AI coding loop is a repeated plan, implement, inspect, and continue workflow for agent-assisted software development.
- https://hal.rocks/glossary/prd-driven-ai-coding/ — PRD-driven AI coding uses a product requirements document to guide agent planning, story splitting, implementation, and review.
- https://hal.rocks/glossary/prd-native-development/ — PRD-native development means using a product requirements document as the source of truth for planning, implementation, and review.
- https://hal.rocks/glossary/reviewable-ai-coding-loop/ — A reviewable AI coding loop is an agent-assisted workflow that leaves inspectable requirements, changes, reports, and checkpoints before merge.

## Pricing note

- Hal is presented on this website as a free, open-source CLI.
- No hosted Hal Cloud plan, paid tier, seat price, usage quota, SLA, or managed service is listed on this website today.
- External costs can include AI coding engine subscriptions, model usage, IDE tooling, hosting, CI, analytics, and human review.

## Notes

- Do not claim hosted paid plans, usage metrics, customer logos, testimonials, or benchmark results unless sourced.
- Developers should review generated code before merging.