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/new-siteadmin-apinpx skills add authgear/authgear-server --skill new-siteadmin-apigit 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/new-siteadmin-api)<a href="https://agentmods.dev/skills/authgear/authgear-server/new-siteadmin-api"><img src="https://agentmods.dev/badge/skills/authgear/authgear-server/new-siteadmin-api.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 | $0.00043 | $0.02263 |
| Opus 5 | $0.00022 | $0.01131 |
| Sonnet 5 | $0.00009 | $0.00453 |
| Haiku 4.5 | $0.00004 | $0.00226 |
Grade A, and why
new-siteadmin-api 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 4d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a new Site Admin API feature: $ARGUMENTS
Follow the stages below in order. Confirm with the user before moving from one stage to the next.
Stage 1: Design and confirm OpenAPI spec
Add the endpoint to docs/api/siteadmin-api.yaml:
- Add the path under
paths:with appropriate HTTP method(s) - Use
$ref: "#/components/responses/BadRequest",Forbidden,NotFoundfor error responses - Add any new request/response schemas to
components/schemas: - Follow existing conventions: snake_case fields, hyphenated paths,
format: datefor date strings
Stop here. Present the spec diff to the user and wait for confirmation before proceeding.
Stage 2: Generate models
make generate
Avoid external type imports:
pkg/siteadmin/model/oapi-codegen.yamlmapsformat: date→stringandformat: email→stringso that nogithub.com/oapi-codegen/runtime/typesimport is generated. If you add a new OpenAPI format that would otherwise pull in an external type, add a mapping tooutput-options.type-mappingin that file before regenerating.
Commit: "[Site Admin] Generate models for <feature>"
Stage 3: Create and wire the handler file
Create pkg/siteadmin/transport/handler_<name>.go. No dummy data — leave ServeHTTP as a stub that returns http.NotFound:
package transport
import "net/http"
func Configure<Name>Route(route httproute.Route) httproute.Route {
return route.WithMethods("OPTIONS", "GET"). // always include "OPTIONS" for CORS preflight
WithPathPattern("/api/v1/...")
}
type <Name>Handler struct {
// Service dependencies added in Stage 5
}
type <Name>Params struct {
// path and query params
}
func parse<Name>Params(r *http.Request) (<Name>Params, error) {
// parse path params via httproute.GetParam(r, "paramName")
// query params: use helpers from params.go (getIntParam, getDateParam, etc.)
// POST body: decode JSON, validate with validation.NewSimpleSchema
}
func (h *<Name>Handler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
_, err := parse<Name>Params(r)
if err != nil {
writeError(w, r, err)
return
}
http.NotFound(w, r)
}
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.
- 4d ago First seen · 232 lines · 43 tokens per session scan A b9b2c1bce614
new-siteadmin-api is a skill published in the GitHub repository authgear/authgear-server (2,017 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 2,263 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.
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.
fastify
Fastify usage for QAuth — plugin authoring (encapsulation, decorators, lifecycle), route schemas with the Zod type provider, production/reverse-proxy setup, and the Fastify version/CVE requirement. Use when adding or modifying @qauth-labs/fastify-plugin- libraries, auth-server routes, or deployment config.