> ## Documentation Index
> Fetch the complete documentation index at: https://jig.fapost.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> What Jig is, who it is for, and how working with it looks.

Jig is a framework for building software with an AI coding agent — Claude Code or Codex. You
describe what you want in plain words; the agent decides how careful the work has to be, keeps
the project's knowledge up to date, and stops to ask you where a human decision matters.

Jig lives inside your project. It adds a folder of project knowledge, a set of skills your agent
uses, and a small command-line tool the agent runs for the mechanical parts. Nothing is hosted,
there is no telemetry, and no script ever calls an AI model: the agent makes the engineering
decisions, the scripts only keep records straight.

## How working with Jig looks

You do not need to learn commands or skill names. You talk to your agent:

> **You:** Add CSV export to the reports page.
>
> **Agent:** This touches the report pipeline and the download endpoint, so I classify it as
> structural (T2): analyze, plan, implement, review, verify. I have created the task
> `csv-export` on its own branch. Here is what I found in the code and the plan …

Behind that answer, the agent picked the `jig-task` skill, looked at the risk of the change,
chose a route, created a task workspace and loaded only the project knowledge relevant to
reports. The agent usually picks the right skill from what you say; when it does not, name it —
`/jig-task` in Claude Code, `$jig-task` in Codex. A one-line typo fix gets a three-step route; a change to authentication gets design, your
approval and an independent review.

## What you get

<CardGroup cols={2}>
  <Card title="Work sized by risk" icon="scale-balanced">
    Five classes, from a typo to a change that touches security or money. The route grows with
    the risk, never with habit.
  </Card>

  <Card title="Knowledge that stays true" icon="book">
    Terms, architecture, rules and decisions live in `.ai/knowledge/` next to the code. Every task
    ends by deciding what it taught the project.
  </Card>

  <Card title="You decide where it matters" icon="user-check">
    At a human gate the agent shows you the design itself — not a summary — and waits.
  </Card>

  <Card title="Your existing docs, adopted" icon="link">
    Rules you already keep in `docs/`, your own ADRs or another tool's instruction files are linked
    in place, not copied.
  </Card>
</CardGroup>

## Where to start

<CardGroup cols={2}>
  <Card title="New project" icon="seedling" href="/greenfield">
    Start from an idea: specification, architecture, rules, then the first tasks.
  </Card>

  <Card title="Existing project" icon="building" href="/brownfield">
    Bring Jig into a codebase you already have, and adopt the documentation it keeps.
  </Card>
</CardGroup>

Jig runs on macOS, Linux and Windows. [Install it](/install) first — one line in a terminal.