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/write-e2e-testnpx skills add authgear/authgear-server --skill write-e2e-testgit clone --depth 1 https://github.com/authgear/authgear-serverWhat 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 | $0.00052 | $0.03837 |
| Opus 5 | $0.00026 | $0.01919 |
| Sonnet 5 | $0.00010 | $0.00767 |
| Haiku 4.5 | $0.00005 | $0.00384 |
Grade A, and why
write-e2e-test 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 — 553 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Follow this guide when writing e2e tests.
E2E Environment Setup
CRITICAL: All make commands must be run from e2e/ directory, not project root.
Standard Workflow
When starting fresh or after code changes:
cd e2e # ← MUST be in e2e directory
make teardown && make setup # ← Tears down old containers, rebuilds binaries, applies migrations
This command:
- Stops and removes Docker containers (Redis, PostgreSQL, Deno hook server)
- Rebuilds authgear and authgear-portal binaries with latest code
- Applies all database migrations
- Starts services fresh
Running Tests
After setup completes, run tests from the e2e directory:
cd e2e # ← Must be in e2e directory
# Run a specific test
go test ./pkg/testrunner/ -count 1 -v -timeout 10m -run "TestAuthflow/<folder>/<filename_without_extension>"
# Run all tests
go test ./pkg/testrunner/ -count 1 -v -timeout 10m
When Setup Fails
If make teardown && make setup fails:
-
Try again - transient Docker issues are common:
cd e2e && make teardown && make setup -
Check if containers are stuck:
docker ps # Run from any directory to list containers -
If still failing - ask the user to manually intervene. Do NOT attempt low-level Docker operations (
docker-compose down -v, etc.) as these can affect other projects and data.
Always use the Makefile (make teardown && make setup). Do not skip to ./run.sh or other workarounds.
When to Re-setup
Always run make teardown && make setup from e2e/ directory when:
- You modified server code (rebuilds binaries)
- Database schema/migrations changed
- Tests fail with DB schema errors
- Starting fresh after a long break
Overview
E2e tests are YAML files placed under e2e/tests/<feature>/. The test runner auto-discovers all *.test.yaml files. Each file defines one test case.
Test File Structure
name: Human-readable test name
authgear.yaml: # Optional: config overrides
extend: path/to/base.yaml # Optional base config
override: |
fraud_protection:
enabled: true
before: # Optional: setup hooks (run before steps)
- type: custom_sql
custom_sql:
path: fixtures.sql
steps:
- name: step name # Optional but recommended
action: create
input: |
{
"type": "signup",
"name": "default"
}
output:
result: |
{
"action": {
"type": "identify"
}
}
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 · 553 lines · 52 tokens per session scan A 9efa0b5f8f5a
write-e2e-test is a skill published in the GitHub repository authgear/authgear-server (2,014 stars, last pushed 6d ago), licensed Apache-2.0. It adds 52 tokens to every session and 3,837 once invoked, about $0.0003 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.