What is microtech-graphql?

A German-language reference for creating and improving GraphQL queries and changes for the microtech ERP system. GraphQL is an API query language; an ERP system manages business data such as products, customers, orders, deliveries, and invoices.

Use it to query or update microtech ERP data, including products, product groups, bills of materials, addresses, contacts, sales documents, invoices, credits, and orders.

It provides documented patterns for reading and changing microtech data without repeatedly working out the API structure. It also includes rules for safe schema inspection and complex operations.

microtech-graphql — Skill for Claude Code and Codex by microtech-gmbh: A German-language reference for creating and improving GraphQL querie

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.

agentmods

npx agentmods add skills/microtech-gmbh/microtech-skills/microtech-graphql

Any agent

npx skills add microtech-gmbh/microtech-skills --skill microtech-graphql

Clone the repo

git clone --depth 1 https://github.com/microtech-gmbh/microtech-skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/microtech-gmbh/microtech-skills/microtech-graphql.svg)](https://agentmods.dev/skills/microtech-gmbh/microtech-skills/microtech-graphql)

Your own site

<a href="https://agentmods.dev/skills/microtech-gmbh/microtech-skills/microtech-graphql"><img src="https://agentmods.dev/badge/skills/microtech-gmbh/microtech-skills/microtech-graphql.svg" alt="Measured on agentmods" height="20"></a>

Per session 337 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 11,494 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00337	$0.11494
Opus 5	$0.00169	$0.05747
Sonnet 5	$0.00067	$0.02299
Haiku 4.5	$0.00034	$0.01149

Measured 4d ago against content hash 2ac71d38811c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

microtech-graphql 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 4d 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.

microtech-graphql/SKILL.md · 1,022 lines

How it starts

The opening of the file, as written. The whole thing — 1,022 lines — stays where its author put it; the contents beside it link to each section on GitHub.

microtech GraphQL - Skill-Referenz

Kompakte Referenz fuer die GraphQL-Schnittstelle des microtech ERP. Optimiert fuer Query-Generierung ueber einen MCP-Server mit graphql_query-Tool.

ASCII: Dieses Dokument verwendet ae/oe/ue/ss statt Umlaute.

WICHTIG - Introspection: NIEMALS das vollstaendige Schema abrufen (__schema). Stattdessen gezielt einzelne Typen abfragen. Siehe references/introspection-guide.md.

Feldkataloge: Fuer detaillierte Feldlisten pro Tabelle siehe references/feldkatalog-*.md.

Erweiterte Themen: Fuer Archiv-Funktionen, externe Bearbeitung, Berechtigungen, Cross-Table-Patterns siehe references/vorgaenge-erweitert.md.

Mutation-Patterns: Fuer Optimistic Locking, rowCopy, ifNotExists, Deep Nesting, Massenoperationen siehe references/mutation-patterns.md.

Query-Patterns: Fuer keyFilter-Details, Arithmetik, skip-Wert, erweitertes @onNull, Schema-Metadaten siehe references/erweiterte-query-patterns.md.

Adressen-Verwaltung: Praxisbeispiele fuer Adressen, Anschriften und Ansprechpartner (lesen, anlegen, aendern, loeschen) mit verschachtelten Links, Optimistic Locking, rowCopy, Massenoperationen und assign-Parametern in references/adressen-verwaltung.md. Bei Adress-Aufgaben dort zuerst nachschlagen!

Parametertabellen: Konfigurations- und Parametertabellen auslesen (Vorgangsarten, Zahlungsbedingungen, Steuerschluessel, Einheiten, Versandarten, Waehrungen, Mahnstufen, Projektstatus u.v.m.) in references/parametertabellen.md. Bei Fragen zur mandantenspezifischen Konfiguration dort nachschlagen!

Workflow-Beispiele: 17 vollstaendige Szenarien (Rechnung erstellen, Vorgang wandeln, Storno, Lagerbestand u.v.m.) in references/workflow-beispiele.md. Bei komplexen Aufgaben dort zuerst nachschlagen!

Kritische Regeln (Top 9)

keyFilter-First: Bei JEDEM Filter zuerst pruefen, ob ein passender by...-Index existiert und keyFilter verwenden. Erst wenn kein passender Index vorhanden ist, auf fastFilter oder slowFilter zurueckfallen. Siehe Abschnitt 5 fuer den verbindlichen Workflow.
@oneOf-Regel: Pro Filterobjekt nur EIN Operator. Mehrere Bedingungen mit and/or kombinieren.
fnPost/fnReverse/fnConvert nur in rowRead-Kontext (nicht rowModify!), immer in mutation.
rowSave vor fnPost - ohne rowSave sind Positionen nicht gespeichert und werden nicht gebucht.
Nach rowSave nicht mehr schreiben im selben Block - fuehrt zu Laufzeitfehler und Rollback.
Leere Belegnummer = Operation fehlgeschlagen - immer fldBelegNr in fn...-Rueckgaben pruefen.
Prozessketten-Integritaet - NIEMALS fn-Funktionen durch manuelle Operationen ersetzen! ERP-Prozessfunktionen (fnPost, fnReverse, fnConvert, fnMoveToArchive) sind die EINZIGE korrekte Art, den Belegstatus zu veraendern. Sie sichern die Prozesskette (z.B. Angebot → AB → Lieferschein → Rechnung), verknuepfen Belege, aktualisieren Lagerbestaende, erzeugen Buchungssaetze und fuehren Plausibilitaetspruefungen durch. Wenn eine fn-Funktion fehlschlaegt, STOPPEN und den Nutzer informieren - KEINEN Workaround versuchen.
NIEMALS rowNew als Ersatz fuer fnConvert - ein manuell angelegter Folgebeleg hat KEINE Verknuepfung zum Vorgaenger. Die Prozesskette ist unterbrochen, Mengen werden nicht korrekt gefuehrt, Lieferstatus wird nicht aktualisiert. Stattdessen: Fehlerursache klaeren (Wandlungspfad nicht konfiguriert, Beleg bereits archiviert, etc.) und Nutzer fragen.
NIEMALS rowDelete als Ersatz fuer fnReverse - eine Loesung per rowDelete umgeht die Storno-Logik: keine Storno-Belegnummer, keine Gegenbuchungen, keine Lagerkorrektur, kein Audit-Trail. Stattdessen: fnReverse verwenden, bei Fehler Nutzer informieren.

Read the full file on GitHub · 1,022 lines

Files

What ships with it

18 files 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.

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.

4d ago First seen · 1,022 lines · 337 tokens per session scan A 2ac71d38811c

Subscribe to this mod's changes

microtech-graphql is a skill published in the GitHub repository microtech-gmbh/microtech-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 337 tokens to every session and 11,494 once invoked, about $0.0017 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 2026-08-31.

Backend and APIs E-commerce agent-skills agentic erp graphql mcp microtech

eliza-app-development

Use when building or changing an elizaOS-based application in this repository. Covers eliza app architecture, monorepo layout, local versus remote versus cloud routing, where to edit features, and non-negotiable runtime constraints. Eliza is the product name of this particular eliza app checkout.

elizaOS/eliza · 65 tokens

live-verify

Two-part gate for gflow-cli feature/fix work. Part 1 (Pre-flight): use when starting work on a gflow-cli feature or fix — confirms the checkout reflects current develop before investing effort. Part 2 (Live-verify): use before claiming gflow-cli work done, especially anything touching a generation code path…

ffroliva/gflow-cli · 100 tokens

generate-domain-model

Generate a complete Mendix domain model in MDL — entities, attributes, associations, enumerations — and validate it. Use when asked for a domain model for a business area (e-commerce, HR, CRM, …) rather than a single entity.

mendixlabs/mxcli · 55 tokens

returns-policy

Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.

strands-agents/samples · 36 tokens

business-context

Maps a business type the user mentions (coffee shop, restaurant, e-commerce, clinic, gym, hotel, school and more) to its industry-standard feature set — POS, inventory, orders, booking, reports, staff — and auto-includes those features with no questions asked. Fuels zero-question planning for /toh-vibe and /toh-plan…

wasintoh/toh-framework · 84 tokens

vendure-cli

Use the Vendure CLI (vendure) to scaffold, run, build, migrate and maintain a Vendure ecommerce project. Use whenever working inside a Vendure project that needs a dev server, a production build, database migrations, plugin/entity/service scaffolding, GraphQL schema generation, diagnostic checks, or codemods.

vendurehq/vendure · 69 tokens