Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/qauth-labs/qauth/auth-enginenpx skills add qauth-labs/qauth --skill auth-enginegit clone --depth 1 https://github.com/qauth-labs/qauthWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00045 | $0.00872 |
| Opus 5 | $0.00023 | $0.00436 |
| Sonnet 5 | $0.00009 | $0.00174 |
| Haiku 4.5 | $0.00005 | $0.00087 |
Grade A, and why
auth-engine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auth Engine Rules
You are working in the QAuth authentication core.
CredentialProvider Pattern
Every authentication method implements the CredentialProvider interface:
// libs/server/federation/src/providers/credential-provider.interface.ts
export interface CredentialProvider {
readonly type: string;
verify(input: unknown): Promise<VerifiedIdentity>;
extractAttributes(result: VerifiedIdentity): UserAttribute[];
}
The auth engine:
- Looks up the credential from
user_credentialsby(realm_id, provider_type, external_sub) - Passes credential data to
provider.verify() - Receives
VerifiedIdentity - Upserts
user_attributesfromprovider.extractAttributes() - Issues tokens with
sub = users.id
The engine does not contain provider-specific logic. Switch/case on provider_type
belongs only in the provider registry, not in service routes.
Current Providers
PasswordProvider(provider_type: 'password') — Phase 1, COMPLETE- Located at
libs/server/federation/src/providers/password.provider.ts externalSubis the normalized email addressassuranceLevel: 'low'— noacrclaim in tokens
- Located at
WalletProvider(provider_type: 'wallet') — T4, IN PROGRESS (Epic #231)- Skeleton shipped (#232):
libs/server/federation/src/providers/wallet.provider.ts verify()throws by design until a validated OID4VP presentation exists — proving key possession is not authentication (see #233); do not wire it into a login path yet
- Skeleton shipped (#232):
Token Claims
sub: alwaysusers.id(UUID) — never email, neverexternal_subemail: fromuser_attributes WHERE attr_key='email' AND verified=true, highest-trust source OMIT entirely if no verified email — do not set nullacr: eIDAS assurance level fromVerifiedIdentity.assuranceLevelOmit for password credentials (assuranceLevel: 'low'→ noacrclaim)- All other claims: from
user_attributes, same trust-ordered resolution
Claim Resolution
// Claim resolution order by source trust level
// wallet > oidc_* > self_reported
const emailAttr = await fastify.repositories.userAttributes.findVerifiedByUserIdAndKey(
userId,
'email'
);
// Returns undefined if no verified email → omit claim from token
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 83 lines · 45 tokens per session scan A b213ef930f0a
auth-engine is a skill published in the GitHub repository qauth-labs/qauth (24 stars, last pushed 7d ago), licensed Apache-2.0. It adds 45 tokens to every session and 872 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
write-e2e-test
Write end-to-end (e2e) tests for authgear-server. Use when the user asks to write, add, or create e2e tests. The tests live in e2e/tests/ and are YAML-driven.
add-portal-screen
Add screens or components to the portal frontend. Use when the user asks to create a new portal page, screen, tab, or UI component.
api-design
Review or design APIs for Authgear. In review mode, evaluates a design draft against the checklist. In ideation mode, develops a design from a description and self-reviews it.
update-deps
Audit and fix dependency vulnerabilities in Go and Node.js packages. Runs govulncheck for Go and npm audit for each package.json directory. Commits fixes directory by directory.
new-siteadmin-api
Full pipeline for adding a new Site Admin API feature — from OpenAPI spec through implementation plan to working service. Use when adding a new endpoint or filling in real data for an existing stub.
update-feature-config
Add or change a feature config field/section in pkg/lib/config (authgear.features.yaml). Use when adding a new feature config field, adding a new top-level section, or touching an existing section's Merge implementation.