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

# Customizing & modifying Synclair

> Yes — you can change any of it. The three-layer model tells you what's yours, what's swappable, and what syncs from upstream.

Short answer: **yes, modify anything.** Your clone is *yours* — it diverges freely and
nothing syncs back automatically. The useful question isn't "can I change it" but
"how do I change it *without* making future foundation updates painful." A simple
three-layer model answers that.

## The three layers

Everything in a Synclair clone is one of three things:

<CardGroup cols={3}>
  <Card title="Brain" icon="brain">
    The portable governance model — token vocabulary, the tiers, the docs contract,
    search, the invention gate, the knowledge layer. **Stable across projects.**
  </Card>

  <Card title="Adapter" icon="plug">
    The platform-specific seams — how a preview is depicted, how tokens are exported,
    how components are distributed. **Swapped per target** (web, React Native, SwiftUI).
  </Card>

  <Card title="Seed" icon="seedling">
    Your project's own content — brand ramps, theme, product name, knowledge, the
    component catalog, the domain skill. **Reseeded per project; never syncs.**
  </Card>
</CardGroup>

## What that means for modifying

| If you're changing…                                | It's…       | Guidance                                                                                                                                                               |
| -------------------------------------------------- | ----------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Brand colors, theme, product name                  | **Seed**    | Change freely — this is *meant* to diverge. It never syncs in either direction.                                                                                        |
| Your components, knowledge, catalog                | **Seed**    | Yours entirely.                                                                                                                                                        |
| Which platform you target                          | **Adapter** | Swap the adapter (web-shadcn by default).                                                                                                                              |
| The hub UI, the token *vocabulary*, the guardrails | **Brain**   | You can change it, but this is what foundation updates touch — so a heavy fork here makes future merges harder. Consider contributing it upstream instead (see below). |

<Note>
  The reseed is a **file/directory operation**, not untangling code. The seed lives in
  known places (`lib/system/seed/`, your theme, your knowledge, your catalog). Swap
  those; keep the rest.
</Note>

## Fit it to your setup

Common "can I make it fit my setup" questions, answered:

* **"Can I run it on a different port / mount path?"** The hub mount point is a single
  swappable constant, and it runs on port 4100 by default — both are yours to change.
* **"Can I target mobile, not web?"** Yes — that's what the adapter layer is for. The
  hub UI stays web/shadcn; only the adapter changes.
* **"Can I add my own skills and agents?"** Yes — that's expected. Just clear the
  capability gate (prove nothing existing covers it) so the set stays coherent.
* **"Can I restructure the hub?"** You can, but that's Brain — see the caution above.

## Keeping the option to pull updates

Because your clone keeps the foundation as a git `upstream` remote, you can *choose*
to pull foundation improvements later — as an ordinary git merge, on your terms.
Modifying **seed** freely costs you nothing here (seed conflicts resolve "keep
ours"). Heavily forking **brain** is what makes that merge harder — so if you find
yourself changing brain, ask whether it's actually a **foundation improvement worth
contributing upstream** rather than a private fork. The `synclair-sync` skill handles
both directions.

<Warning>
  Nothing syncs automatically — not foundation updates *into* your clone, and never your
  **seed** in either direction. Your brand, domain, and knowledge stay yours. Pulling
  updates is always a deliberate act.
</Warning>

<Card title="Still have questions?" icon="list-check" href="/faq">
  The fast-answer FAQ covers the rest.
</Card>