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/level09/enferno/enferno-devnpx skills add level09/enferno --skill enferno-devgit clone --depth 1 https://github.com/level09/enfernoWrote 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/level09/enferno/enferno-dev)<a href="https://agentmods.dev/skills/level09/enferno/enferno-dev"><img src="https://agentmods.dev/badge/skills/level09/enferno/enferno-dev.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 | $0.00082 | $0.01455 |
| Opus 5 | $0.00041 | $0.00727 |
| Sonnet 5 | $0.00016 | $0.00291 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
enferno-dev 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const res = await axios.get('/api/products', { params: { page, per_page: itemsPerPage } }); How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enferno Development
Flask + Vue 3 + Vuetify 3 framework. No build step. SQLAlchemy 2.x patterns.
Quick Reference
uv run flask run --port 5001 # Dev server (5001 on macOS)
uv run flask create-db # Init database
uv run flask install # Create admin user
uv run ruff check . && uv run ruff format . # Lint + format
Blueprint Structure
enferno/
├── feature_name/
│ ├── views.py # Routes and API endpoints
│ ├── models.py # SQLAlchemy models
│ └── forms.py # WTForms (if needed)
├── templates/
│ └── feature_name/ # Jinja templates
Register in app.py:
from enferno.feature_name.views import bp as feature_bp
app.register_blueprint(feature_bp)
Models
Use BaseMixin and implement to_dict()/from_dict() on instances:
from enferno.extensions import db
from enferno.utils.base import BaseMixin
class Product(db.Model, BaseMixin):
__tablename__ = "products"
id = db.Column(db.Integer, primary_key=True)
name = db.Column(db.String(255), nullable=False)
price = db.Column(db.Numeric(10, 2))
active = db.Column(db.Boolean, default=True)
def to_dict(self):
return {"id": self.id, "name": self.name, "price": float(self.price), "active": self.active}
def from_dict(self, data):
self.name = data.get("name", self.name)
self.price = data.get("price", self.price)
self.active = data.get("active", self.active)
return self
API Endpoints
Standard CRUD pattern with pagination and {item: ...} payloads:
from flask import Blueprint, request
from flask_security import roles_required, current_user
from enferno.extensions import db
from enferno.user.models import Activity
bp = Blueprint("products", __name__)
@bp.before_request
@auth_required("session")
@roles_required("admin")
def before_request():
pass
@bp.get("/api/products")
def list_products():
page = request.args.get("page", 1, type=int)
per_page = request.args.get("per_page", 25, type=int)
query = db.select(Product)
pagination = db.paginate(query, page=page, per_page=per_page)
return {"items": [p.to_dict() for p in pagination.items], "total": pagination.total, "perPage": per_page}
@bp.post("/api/product/")
def create_product():
data = request.json.get("item", {})
product = Product().from_dict(data)
db.session.add(product)
db.session.commit()
Activity.register(current_user.id, "Product Create", product.to_dict())
return {"item": product.to_dict()}
@bp.post("/api/product/<int:id>")
def update_product(id):
product = db.get_or_404(Product, id)
old = product.to_dict()
product.from_dict(request.json.get("item", {}))
db.session.commit()
Activity.register(current_user.id, "Product Update", {"old": old, "new": product.to_dict()})
return {"item": product.to_dict()}
@bp.delete("/api/product/<int:id>")
def delete_product(id):
product = db.get_or_404(Product, id)
Activity.register(current_user.id, "Product Delete", product.to_dict())
db.session.delete(product)
db.session.commit()
return {"deleted": True}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 216 lines · 82 tokens per session scan A f8649334006f
enferno-dev is a skill published in the GitHub repository level09/enferno (569 stars, last pushed 9d ago), licensed MIT. It adds 82 tokens to every session and 1,455 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
newsblur-cli
Manage your NewsBlur from the terminal. Read feeds, search stories, save and share articles, train intelligence classifiers, discover new feeds, and automate workflows with the NewsBlur CLI. Use when the user wants to interact with their NewsBlur account, check feeds, manage subscriptions, or build scripts around…
make-interfaces-feel-better
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel…
python-backend
Production Python async patterns including asyncio TaskGroup, FastAPI dependency injection and middleware, SQLAlchemy 2.0 async sessions, and database connection pool tuning. Python 3.11+ runtime concerns such as ExceptionGroup, cancellation semantics, and session rollback. Use when building async services, wiring…
frontend-conventions
Frontend convention reference (SvelteKit / Svelte 5). Auto-injected into frontend-aware agents - not user-invocable.
figma-use
MANDATORY prerequisite — you MUST invoke this skill BEFORE every usefigma tool call. NEVER call usefigma directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in…
cli-creator
Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a…