Authgear is an open-source identity and authentication service that provides login, account management, multi-factor authentication, passkeys, and single sign-on for applications. SaaS and mobile-app developers can run it themselves or use Authgear Cloud to manage consumer and enterprise user access. The catalogue entries relate to operating and configuring Authgear's authentication workflows.
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/authgear/authgear-server/update-feature-confignpx skills add authgear/authgear-server --skill update-feature-configgit clone --depth 1 https://github.com/authgear/authgear-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/authgear/authgear-server/update-feature-config)<a href="https://agentmods.dev/skills/authgear/authgear-server/update-feature-config"><img src="https://agentmods.dev/badge/skills/authgear/authgear-server/update-feature-config.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00048 | $0.01916 |
| Opus 5 | $0.00024 | $0.00958 |
| Sonnet 5 | $0.00010 | $0.00383 |
| Haiku 4.5 | $0.00005 | $0.00192 |
Grade A, and why
update-feature-config 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 5d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Feature Config
Feature config (authgear.features.yaml) is merged across layers — code
default ← cluster ← plan ← app override — via FeatureConfig.Merge
(pkg/lib/config/feature.go), which reflects over every top-level field and
dispatches to that section's own Merge in pkg/lib/config/feature_*.go.
Hard requirement: merge must be field-level, never whole-section replace
Historically, most sections implemented Merge as a wholesale swap:
// WRONG for any section with more than one leaf field
func (c *XFeatureConfig) Merge(layer *FeatureConfig) MergeableFeatureConfig {
if layer.X == nil {
return c
}
return layer.X
}
This is a real, reachable bug class, not a theoretical one: if a lower layer
(e.g. a plan) sets field A and a higher layer (e.g. an app override) later
sets a sibling field B — without repeating A — the whole-section swap
silently resets A back to its code default. Plan/app documents are
routinely partial, hand-authored YAML, so this triggers in practice, not just
in edge cases. It was found and fixed across identity, authentication,
authenticator, ui, hook, collaborator, messaging.rate_limits, and
test_mode — do not reintroduce it in a new section or a new field on an
existing section.
Every new field on an existing multi-field section, and every new top-level section, must merge field-level:
- Follow the reference pattern in
OAuthClientFeatureConfig.Merge(pkg/lib/config/feature_oauth.go): nil-safe guards first (if c == nil && layer == nil { return nil },if c == nil { return layer },if layer == nil { return c }), then per-fieldif layer.X != nil { c.X = layer.X }for every field. - If a section/sub-object genuinely has only one field, a whole-object
replace at that level is fine — there's nothing else to lose. But if that
one field is itself an object with siblings further down, cascade the
field-level merge all the way down to where the real siblings are, even
through single-field wrapper levels. See
feature_authenticator.go'sAuthenticator → Password → Policycascade:AuthenticatorandPasswordeach have only one field, butPolicyhas three siblings that must merge independently — so the cascade goes three levels deep, not stopping at the first single-field level. - Never write
if layer.Section == nil { return c }; return layer.Sectionfor a section with more than one leaf field, directly or transitively.
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.
- 5d ago First seen · 142 lines · 48 tokens per session scan A 979194c4c4e9
update-feature-config is a skill published in the GitHub repository authgear/authgear-server (2,024 stars, last pushed today), licensed Apache-2.0. It adds 48 tokens to every session and 1,916 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
auth0-docs
Auth0 — identity platform: auth flows, Universal Login, SSO, identity providers, MFA, RBAC, Actions, tokens.
zeroid
MANUAL TRIGGER ONLY: invoke only when user types /zeroid. Identity infrastructure for AI agents — register identities, issue tokens, delegate to sub-agents, revoke credentials, and manage credential policies via the Zeroid REST API.
zeroid
Identity infrastructure for AI agents — register identities, issue tokens, delegate to sub-agents, revoke credentials, manage policies.
cis-aws-database-2.10
Ensure Database has IAM Auth is Enabled.
auth-oauth
Implements and reviews OAuth 2.0/2.1 flows following RFC 6749, RFC 9700 (BCP), and PKCE (RFC 7636). Use when implementing authorization code flow, token handling, client registration, or securing OAuth endpoints.
schema
Database schema rules for QAuth. Use when working with the identity model, Drizzle ORM, migrations, repositories, or claim resolution. Reflects the CURRENT shipped schema — the identifier-abstraction model (ADR-002, IMPLEMENTED via Epic.