OnboardingCAUTION
A framework for building agentic apps
Overview
A framework for building agentic apps
d31edd75948aOBSERVED · 2026-10-14What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: onboarding
description: >-
How to register user-facing setup steps (API keys, OAuth, connecting
third-party services) for the sidebar setup checklist. Use when adding a
feature that needs initial user configuration.
scope: dev
metadata:
internal: true
---
# Onboarding Steps
## Rule
If a feature requires user-facing setup (API keys, OAuth, connecting a third-party service), register an onboarding step so it appears in the agent sidebar's setup checklist.
Onboarding must point users to a secure credential path; it must never encode
the credential value in source, docs, fixtures, prompts, or generated content.
For a provider represented in the workspace connection catalog, check the
connection readiness and app grant first, then resolve credentials through the
scoped workspace-connection helper. Only when no reusable connection exists
should API keys and service tokens use `registerRequiredSecret()` from the
`secrets` skill. For OAuth, check the scoped OAuth token store. Use deployment
env vars only for deploy-level configuration, not per-user credentials.
Model onboarding around the logical connection outcome, not its individual
fields. Because `registerRequiredSecret({ required: true })` auto-injects a
checklist item per registration, do not mark every credential/config field as
required by reflex. Use one composite onboarding step or connection readiness
check when several values are needed for one provider.
A custom setup page is appropriate only when it adds provider-specific
prerequisites, sequencing, or health checks. Keep it as a thin guide over the
shared settings, vault, OAuth, and action surfaces; never make it a second place
that stores or manages credentials.
## Registering a Step
```ts
import { registerOnboardingStep } from "@agent-native/core/onboarding";
import { hasOAuthTokens } from "@agent-native/core/oauth-tokens";
registerOnboardingStep({
id: "gmail",
order: 100,
title: "Connect Gmail",
description: "Grant read/send access.",
methods: [
{
id: "oauth",
kind: "link",
primary: true,
label: "Sign in with Google",
payload: { url: "/_agent-native/google/auth-url" },
},
],
isComplete: async (ctx) =>
ctx?.userEmail ? hasOAuthTokens("google", ctx.userEmail) : false,
});
```
See `packages/core/docs/content/onboarding.md` for method kinds and built-in steps.
For S3-compatible file storage, declare a `kind: "file-storage"` method instead
of a `form` with `S3_*` fields. It renders the shared `StorageSettingsForm`,
which saves through the `manage-file-storage` action (owners and admins only),
so onboarding, Settings, and templates cannot drift into different rules. A
provider that serves files without a public URL sets
`publicBaseUrlOptional: true` on its `FileUploadProvider`.
## Shared services: one list for first-run and Infrastructure
`WORKSPACE_SERVICES` (`packages/core/src/onboarding/workspace-services.ts`,
exported from `@agent-native/core/onboarding`) is the one list of services
every app shares: AI model, storage, voice, images, embeddings, and the
Builder.io-only services. First-run "Choose your setup" reads it through
`getOnboardingAppProfile()`, which tags each capability with its `service` id
(and `builderOnly`). Settings › Organization › Infrastructure renders one
Services row per entry and takes its Required/Recommended tags from those ids.
- To add a shared service, add it to `WORKSPACE_SERVICES` and give it a row in
`InfrastructureSettingsPage.tsx`; its records are keyed by service id, so
the page won't compile without one. Never add a label to first-run alone.
- To tailor a service for one app, declare a capability in that app's profile
with one of the service's `capabilityIds` (Clips' `video-storage`). It
replaces the default copy and can raise the tag, never lower it.
- An app's own capabilities (a Figma token, a Gmail connection) stay out of
`WORKSPACE_SERVICES`. First-run shows them only when required or suggested.
- List a Builder.io capability only if Builder.io actually powers it in code.
Transactional email is deployment configuration, not an onboarding form. The
built-in `email` step links to the host variables (`RESEND_API_KEY` or
`SENDGRID_API_KEY`, plus `EMAIL_FROM`) and is hidden when the deployment
already provides email. Don't add a step that saves those keys.
## Related Skills
- `adding-a-feature` — The four-area checklist; onboarding is often part of a new integration
- `authentication` — Most onboarding steps involve OAuth or credentialsTrust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
.agents/skills/an
.agents/skills/content-product-development
.agents/skills/design-exploration
.agents/skills/turn-into-app
.agents/skills/visual-edit
Gates applied: no_behavioural_pass.
d31edd75948afull audit observations/trust-audit/skill/builderio__onboarding.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-14 | d31edd75948a | CAUTION | B | 89 | first audit |
Questions
What does the Onboarding skill do?
A framework for building agentic apps
Is Onboarding safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Onboarding access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (d31edd75948a), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.
Add this badge to your README
Shows this page's audit result and links back to it. It updates when the audit does.
[](https://modelsatlas.com/skills/builderio/onboarding/)
Not your listing, or something out of date? Claim or update your listing.