authgear-server: Skill for Claude Code

.claude/skills/update-configs/SKILL.md

update-configs is a skill for Claude Code from authgear/authgear-server. It costs 77 tokens per session (4,073 once invoked), scanned A, original, Apache-2.0.

A guide for changing the project's YAML configuration files and their Go types, schemas, and test data. It covers project settings, feature settings, and secrets.

In plain words
What is it for?
Use it when adding or changing a configuration field, section, feature flag, or secret key in the project's config package.
Why use it?
It helps prevent an apparently small configuration change from leaving one of the three formats or its required tests out of sync.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is authgear/authgear-server's own configuration. It tells Claude Code how to work on authgear-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything authgear-server configures →

About the project

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.

authgear/authgear-server · 2,133 stars · on GitHub · authgear.com

Reuse

Borrowing it

Nothing to install: this file belongs to authgear/authgear-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/authgear/authgear-server/main/.claude/skills/update-configs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/authgear/authgear-server

Made for: Claude Code.

Wrote 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.

agentmods badge for update-configs

README.md
[![agentmods](https://agentmods.dev/badge/skills/authgear/authgear-server/update-configs/github.svg)](https://agentmods.dev/skills/authgear/authgear-server/update-configs)
Your own site
<a href="https://agentmods.dev/skills/authgear/authgear-server/update-configs"><img src="https://agentmods.dev/badge/skills/authgear/authgear-server/update-configs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for update-configs

Your own site · 80×15
<a href="https://agentmods.dev/skills/authgear/authgear-server/update-configs"><img src="https://agentmods.dev/badge/skills/authgear/authgear-server/update-configs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,073 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00077 $0.04073
Opus 5.5 $0.00031 $0.01629
Sonnet 5.5 $0.00015 $0.00815
Haiku 4.5 $0.00008 $0.00407

Measured 29d ago against content hash 5cc6bd590ae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update-configs 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 29d 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.

.claude/skills/update-configs/SKILL.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Configs

pkg/lib/config backs three separate documents, each with its own Go types, its own JSON schema, and its own required testdata coverage. Get the surface right first — the rest of this skill is organized by surface.

Surface Document Go types Parsed/validated by
Project config authgear.yaml AppConfig, pkg/lib/config/*.go (non-feature_/secret_ files) config.Parse (schema + AppConfig.Validate)
Feature config authgear.features.yaml FeatureConfig, pkg/lib/config/feature_*.go config.ParseFeatureConfig (schema) + FeatureConfig.Merge
Secrets authgear.secrets.yaml SecretConfig, pkg/lib/config/secret_*.go config.ParseSecret (schema) + SecretConfig.Validate (cross-checked against AppConfig)

A single feature often touches more than one surface at once (e.g. a new app-config section gated by a feature-config flag, or an app-config section backed by a secret) — apply the relevant part of each section below for every surface the change touches, don't stop at the first one.

Hard requirement: every surface has a required testdata file

This is the single most commonly missed step. Each surface's schema and validation behavior is exercised by a shared, hand-maintained testdata fixture — a YAML file of name/error/config cases, each parsed through the real production parser and asserted against an exact expected error (or null). Adding or changing a field's schema, a validation rule, or anything that changes what does or doesn't parse without adding a case to the matching file is an incomplete change, not a smaller one — it looks done because the code compiles and existing tests pass, but nothing actually exercises the new behavior.

Surface Required testdata file Consuming test
Project config pkg/lib/config/testdata/config_tests.yaml TestAppConfig (config_test.go)
Feature config (schema) pkg/lib/config/testdata/parse_feature_tests.yaml TestParseFeatureConfig (feature_test.go)
Feature config (merge) pkg/lib/config/testdata/merge_feature.yaml see "Required test coverage" under Feature config below
Secrets (schema) pkg/lib/config/testdata/parse_secret_tests.yaml TestParseSecret (secret_test.go)
Secrets (cross-validation against app config) pkg/lib/config/testdata/secret_config_validate_tests.yaml TestSecretConfigValidate (secret_test.go)

Read the full file on GitHub · 298 lines

Changes

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.

  1. 29d ago First seen · 298 lines · 77 tokens per session scan A 5cc6bd590ae1

Subscribe to this mod's changes

update-configs is a skill published in the GitHub repository authgear/authgear-server (2,133 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 4,073 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-30.

Related

Other skills, from other repositories

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.

highflame-ai/zeroid · 51 tokens

configuring-oauth2-authorization-flow

Configure secure OAuth 2.0 authorization flows including Authorization Code with PKCE, Client Credentials, and Device Authorization Grant. This skill covers flow selection, PKCE implementation, token.

26zl/cybersec-toolkit · 44 tokens

auth0-docs

Auth0 — identity platform: auth flows, Universal Login, SSO, identity providers, MFA, RBAC, Actions, tokens.

pledgeandgrow/pledge-skills · 32 tokens

totp-oauth

Fermi's own OAuth 2.0 + TOTP owner authentication - how clients connect, how the 2FA login works, and how to roll it back.

abel30567/fermi-mcp · 38 tokens

keycloak-migration-doctor

Preflight a Keycloak export, import or migration on a Skycloak-managed cluster against the known blockers, and diagnose a job that already failed by reading the failure reason the API records but the dashboard notice does not show. Use when an export or import fails, a migration stalls, or before moving realm data in…

sky-cloak/skycloak-mcp · 72 tokens

configuring-oauth2-authorization-flow

Configure secure OAuth 2.0 authorization flows including Authorization Code with PKCE, Client Credentials, and Device Authorization Grant. This skill covers flow selection, PKCE implementation, token.

andycungkrinx91/konoha · 44 tokens