agentmods.dev

get-started

get-started is a skill for Claude Code from pitwch/pfx-mcp-server. It costs 59 tokens per session (380 once invoked), scanned A, original, MIT.

A setup guide for connecting Claude to Proffix Px5, a business system used for records and enterprise resource planning. It explains the required access key and Proffix login details before searches or queries can run.

In plain words
What is it for?
Use it when configuring Proffix access, searching addresses, or running read-only ERP queries.
Why use it?
It prevents failed requests caused by missing credentials and helps keep sensitive keys and passwords out of the chat.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pfx-mcp-remote plugin — 1 skill, 1 MCP server shipped together

not rated 2repo changed yesterday A scan 59 tokens original MIT

Good fit Use it when configuring Proffix access, searching addresses, or running read-only ERP queries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pitwch/pfx-mcp-server/get-started
View source ↗ pitwch/pfx-mcp-server
Install

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.

Any agent
npx skills add pitwch/pfx-mcp-server --skill get-started
Clone the repo
git clone --depth 1 https://github.com/pitwch/pfx-mcp-server

Made for: Claude Code.

Or install pfx-mcp-remote, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

Wrote 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.

agentmods badge for get-started

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitwch/pfx-mcp-server/get-started/github.svg)](https://agentmods.dev/skills/pitwch/pfx-mcp-server/get-started)
Your own site
<a href="https://agentmods.dev/skills/pitwch/pfx-mcp-server/get-started"><img src="https://agentmods.dev/badge/skills/pitwch/pfx-mcp-server/get-started/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.

agentmods 80×15 button for get-started

Your own site · 80×15
<a href="https://agentmods.dev/skills/pitwch/pfx-mcp-server/get-started"><img src="https://agentmods.dev/badge/skills/pitwch/pfx-mcp-server/get-started.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00380
Opus 5.5 $0.00024 $0.00152
Sonnet 5.5 $0.00012 $0.00076
Haiku 4.5 $0.00006 $0.00038

Measured yesterday against content hash 852c7f79b185, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

get-started 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 yesterday.

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.

plugins/pfx-mcp-remote/skills/get-started/SKILL.md · 32 lines

What it actually says

Proffix Px5 (pfx-mcp) — Remote

Sprache

Antworte immer in der Sprache der letzten Nutzernachricht. Deutsch bleibt Deutsch, Englisch bleibt Englisch, Franzoesisch bleibt Franzoesisch. Fachbegriffe (API-Key, Proffix, Datenbank, Port) duerfen bleiben.

Anmeldung (OAuth)

Dieser Connector laeuft remote auf https://mcp.pfx.ch. Die Anmeldung erfolgt ueber OAuth auf der sicheren Connect-Seite von mcp.pfx.ch — nicht im Chat.

  1. Wenn keine pfx-Tools verfuegbar sind oder ein Aufruf 401/403 liefert: den Nutzer die Verbindung ueber den OAuth-Dialog herstellen lassen. Dort gibt er ein:
  2. API-Key und Passwort nie im Chat verlangen und nie wiederholen.
  3. Key, Datenbank und listeNr nie erfinden.

Smoke

Sobald der Nutzer bestaetigt, dass die Verbindung steht, einen Lese-Aufruf ausfuehren (z. B. eine Adresssuche mit einem Namen, den er nennt). Reports (px_generate_report) einzeln ausfuehren. Anlegen, Aendern und Loeschen erst nach ausdruecklicher Bestaetigung.

Changes

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.

  1. yesterday Changed · +7 lines · +5 tokens per session 852c7f79b185
  2. 6d ago First seen · 25 lines · 54 tokens per session scan A 49f8edb3b364

Subscribe to this mod's changes

get-started is a skill published in the GitHub repository pitwch/pfx-mcp-server (2 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 380 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-05.

Backend and APIs
Related

get-started compared with skills from other repositories

get-started next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
get-startedpitwch/pfx-mcp-serverSkill22d agoMITA59Claude Code
mem0-oss-to-platformmem0ai/mem0Skill69k5d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2kyesterdayMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2kyesterdayMITA46Claude Code
dev-runtimelangwatch/langwatchSkill5.0ktodayApache-2.0A172Claude Code
api-designericrisco/rsc-harnessSkill579yesterdayMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill2572d agoMITA106Claude Code