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/benja-pauls/serpentstack/authnpx skills add Benja-Pauls/SerpentStack --skill authgit clone --depth 1 https://github.com/Benja-Pauls/SerpentStackWhat 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 | $0.01558 |
| Opus 5 | $0.00024 | $0.00779 |
| Sonnet 5 | $0.00010 | $0.00312 |
| Haiku 4.5 | $0.00005 | $0.00156 |
Grade A, and why
auth scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://localhost:8000/api/v1/auth/register \ How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auth
SerpentStack ships with working local JWT authentication (register, login, token validation). This skill explains the auth architecture and how to swap providers.
How Auth Works (Built-in)
Architecture
POST /api/v1/auth/register → UserService.register() → bcrypt hash → DB → JWT
POST /api/v1/auth/login → UserService.authenticate() → verify hash → JWT
GET /api/v1/auth/me → get_current_user dependency → decode JWT → UserResponse
Any protected route:
@router.delete("/{id}")
async def delete(user: UserInfo = Depends(get_current_user)):
# user.user_id, user.email available here
Key Files
| File | Role |
|---|---|
backend/app/routes/auth.py |
Auth routes + get_current_user dependency |
backend/app/services/user.py |
Registration, authentication, password hashing |
backend/app/models/user.py |
User SQLAlchemy model (email, hashed_password) |
backend/app/schemas/user.py |
Request/response schemas (register, login, token) |
backend/app/middleware/auth.py |
Optional global auth middleware (not enabled by default) |
The UserInfo Contract
All protected routes receive a UserInfo object via dependency injection:
class UserInfo(BaseModel):
user_id: str
email: str | None = None
name: str | None = None
raw_claims: dict[str, Any] = {}
This is the interface between auth and the rest of the app. When swapping providers, keep this shape — every route that uses Depends(get_current_user) depends on it.
Protecting a Route
Add Depends(get_current_user) to any route that requires authentication:
from app.routes.auth import UserInfo, get_current_user
@router.post("")
async def create_thing(
payload: ThingCreate,
user: UserInfo = Depends(get_current_user), # ← requires valid JWT
db: AsyncSession = Depends(get_db),
service: ThingService = Depends(get_thing_service),
) -> ThingResponse:
thing = await service.create(payload, owner_id=user.user_id)
await db.commit()
return ThingResponse.model_validate(thing)
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 · 186 lines · 48 tokens per session scan A a555887974cf
auth is a skill published in the GitHub repository Benja-Pauls/SerpentStack (2 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 1,558 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.