Borrowing it
Nothing to install: this file belongs to j4th/mtg-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/j4th/mtg-mcp-server/main/.claude/skills/new-provider/SKILL.mdgit clone --depth 1 https://github.com/j4th/mtg-mcp-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/j4th/mtg-mcp-server/new-provider)<a href="https://agentmods.dev/skills/j4th/mtg-mcp-server/new-provider"><img src="https://agentmods.dev/badge/skills/j4th/mtg-mcp-server/new-provider/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/j4th/mtg-mcp-server/new-provider"><img src="https://agentmods.dev/badge/skills/j4th/mtg-mcp-server/new-provider.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00019 | $0.00776 |
| Opus 5 | $0.00010 | $0.00388 |
| Sonnet 5 | $0.00004 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
new-provider 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- new-provider — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Provider
Scaffold a new backend provider with all required files following project conventions.
Usage
/new-provider <name>
Examples:
/new-provider scryfall/new-provider spellbook/new-provider seventeen_lands/new-provider edhrec
What Gets Created
Given /new-provider <name>:
1. Service client: src/mtg_mcp_server/services/<name>.py
import structlog
from mtg_mcp_server.services.base import DEFAULT_USER_AGENT, BaseClient, ServiceError
log = structlog.get_logger(service="<name>")
class <Name>Error(ServiceError): ...
class <Name>NotFoundError(<Name>Error): ...
class <Name>Client(BaseClient):
"""<Name> API client."""
def __init__(
self,
base_url: str = "...", # from Settings
rate_limit_rps: float = ...,
user_agent: str = DEFAULT_USER_AGENT,
) -> None:
super().__init__(
base_url=base_url,
rate_limit_rps=rate_limit_rps,
user_agent=user_agent,
)
2. Provider sub-server: src/mtg_mcp_server/providers/<name>.py
from fastmcp import FastMCP
from fastmcp.server.lifespan import lifespan
from fastmcp.exceptions import ToolError
from mtg_mcp_server.config import Settings
from mtg_mcp_server.providers import TOOL_ANNOTATIONS
from mtg_mcp_server.services.<name> import <Name>Client
_client: <Name>Client | None = None
@lifespan
async def <name>_lifespan(server: FastMCP):
global _client
settings = Settings()
client = <Name>Client(base_url=settings.<name>_base_url)
async with client:
_client = client
yield {}
_client = None
<name>_mcp = FastMCP("<DisplayName>", lifespan=<name>_lifespan)
def _get_client() -> <Name>Client:
if _client is None:
raise RuntimeError("<Name>Client not initialized — server lifespan not running")
return _client
# Tools go here — each uses:
# annotations=TOOL_ANNOTATIONS
# client = _get_client()
# ToolError for error responses
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.
- 8d ago First seen · 107 lines · 19 tokens per session scan A aef5fb2754e7
new-provider is a skill published in the GitHub repository j4th/mtg-mcp-server (20 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 776 once invoked, about $0.0001 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
kingdee-mcp-dev
Knowledge base for the Kingdee MCP Dev Squad. Covers how to integrate the Kingdee Cloud Star OpenAPI (ApiDoc) interfaces into the kingdee-mcp Python+FastMCP project: WebAPI login/metadata caching, field-discovery SOP, 二开 (customized) bill pitfalls, and the ApiDoc coverage tracking template.
MCP Server Builder
Step-by-step guidance for creating a new MCP server with FastMCP or the TypeScript SDK — tool definitions, resource handlers, error responses, and usage examples.
home-assistant-rest
Control and query Home Assistant through the connector's callservice tool — REST API patterns, common domains, how to find entities before acting.
rest-api-conventions
Design predictable REST APIs — noun resources, correct status codes, pagination, consistent errors, and versioning.
typescript-craftsmanship
Professional TypeScript + React + Next.js coding standards enforcer. Use this skill whenever writing, reviewing, or refactoring TypeScript code in any project — whether it's a new feature, a bug fix, a refactoring pass, or a code review. Trigger on: any TypeScript or TSX file creation/editing, "clean up this code"…
mtg-commander-analysis
Expert Magic: The Gathering Commander (EDH) deck analysis, optimization, and building assistant. Use this skill whenever the user asks about Commander decks, EDH optimization, power level assessment, bracket placement, mana base construction, card cuts/additions, deck building, commander selection, synergy analysis…