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 skills add iloveitaly/llm-ide-rules --skill fastapi_stripegit clone --depth 1 https://github.com/iloveitaly/llm-ide-rulesWrote 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/iloveitaly/llm-ide-rules/fastapi_stripe)<a href="https://agentmods.dev/skills/iloveitaly/llm-ide-rules/fastapi_stripe"><img src="https://agentmods.dev/badge/skills/iloveitaly/llm-ide-rules/fastapi_stripe/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.
<a href="https://agentmods.dev/skills/iloveitaly/llm-ide-rules/fastapi_stripe"><img src="https://agentmods.dev/badge/skills/iloveitaly/llm-ide-rules/fastapi_stripe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00009 | $0.00869 |
| Opus 5 | $0.00005 | $0.00434 |
| Sonnet 5 | $0.00002 | $0.00174 |
| Haiku 4.5 | $0.00001 | $0.00087 |
Grade A, and why
fastapi_stripe 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 10d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fastapi_Stripe
A Stripe Checkout implementation takes four steps:
- Create a checkout session. Happens when the user visits the checkout page.
- Create a pending order. Happens right before the user is sent to Stripe.
- Complete the order. Happens when the user is redirected back to the app after payment.
- Check the order status. Happens when the user visits the confirmation page, which could happen multiple times.
Here's an example implementation:
from .configuration import stripe_client, origin_url
@screening_api_app.post("/")
def create_order_session(
request: Request,
) -> str:
"""
Creates a checkout session. This happens after the user visits
the checkout page.
"""
session = stripe_client.v1.checkout.sessions.create(
params={
"ui_mode": "custom",
"line_items": [
{
"price": "price_123",
"quantity": 1,
}
],
"mode": "payment",
# CHECKOUT_SESSION_ID is a placeholder for the actual session id, which is replaced by Stripe
# cannot use include_query_params because the Stripe checkout template variable is escaped
"return_url": (
# `request` required for abs URL generation
str(request.url_for("complete_ticket_purchase"))
+ "?session_id={CHECKOUT_SESSION_ID}"
),
}
)
return session.client_secret
class PendingOrderRequest(BaseModel):
stripe_checkout_session_id: str
email: str
# and other fields...
@screening_api_app.post("/pending")
def create_pending_order(
data: PendingOrderRequest,
distribution: Distribution = Depends(get_distribution_by_host),
) -> TypeID:
"""
Right before we pass off the user to Stripe, we save all order information.
This can happen multiple times if there is a form submission error with Stripe.
This pending step is in place largely because many payment methods require a redirect to a confirmation page,
so we assume we'll always be redirected.
The database schema ensures duplicate stripe checkout session ids never happen.
"""
# let's validate the stripe checkout session id is real
stripe_session = stripe_client.v1.checkout.sessions.retrieve(
data.stripe_checkout_session_id
)
if stripe_session.status != "open":
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="Your checkout session has expired. Please refresh the page and try again.",
)
order = Order.one_or_none(
stripe_checkout_session_id=data.stripe_checkout_session_id
)
if order:
order.email = data.email
# ...and other fields...
order.save()
else:
order = Order(
stripe_checkout_session_id=data.stripe_checkout_session_id,
email=data.email,
).save()
return order.id
@screening_api_app.get("/complete")
def complete_ticket_purchase(
request: Request,
session_id: str = Query(),
):
stripe_session = stripe_client.v1.checkout.sessions.retrieve(session_id)
if stripe_session.status != "complete":
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND)
order = Order.one(stripe_checkout_session_id=session_id)
order.status = OrderState.paid
order.save()
redirect_url = (
f"{origin_url}/screening/{order.screening_id}/confirmation/{session_id}"
)
return RedirectResponse(url=redirect_url)
@screening_api_app.get("/confirmation")
def ticket_purchase_status(
request: Request,
stripe_checkout_session_id: str = Query(),
screening_id: TypeID = Query(),
) -> str:
stripe_client = distribution.stripe_client()
stripe_session = stripe_client.v1.checkout.sessions.retrieve(
stripe_checkout_session_id
)
if stripe_session.status != "complete":
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail="Checkout is not complete",
)
order = Order.one(stripe_checkout_session_id=stripe_checkout_session_id)
return order.id
public_api_app.include_router(screening_api_app)
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.
- 10d ago First seen · 147 lines · 9 tokens per session scan A 41605f9c9437
fastapi_stripe is a skill published in the GitHub repository iloveitaly/llm-ide-rules (13 stars, last pushed 2d ago), licensed MIT. It adds 9 tokens to every session and 869 once invoked, about $0.0000 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
agent-platform-prompt-management
Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent Platform. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform prompts.
buywhere-product-catalog
Use BuyWhere's MCP and API surfaces to add product search, price comparison, and deal discovery to AI shopping agents.
llm-application-dev-prompt-optimize
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati.
arize-prompt-optimization
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output…
gemini-interactions-api
Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. This skill covers the Interactions API, the…
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.