bueroassistent

bueroassistent is a skill for Claude Code, Codex from ellmos-ai/bach. It costs 64 tokens per session (1,200 once invoked), scanned A, original, MIT.

An office-management assistant for tax records, funding plans, professional documents, work organization, and schedules.

In plain words
What is it for?
Use it to record and categorize receipts, document deductible work expenses, prepare yearly tax summaries and exports, create funding plans, research materials, and organize office documents.
Why use it?
It brings tax, funding, and documentation work into one organized process and stores records in separate work folders.

Skill for Claude CodeCodex

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/ellmos-ai/bach/bueroassistent
Any agent
npx skills add ellmos-ai/bach --skill bueroassistent
Clone the repo
git clone --depth 1 https://github.com/ellmos-ai/bach

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.

agentmods badge for bueroassistent

README.md
[![agentmods](https://agentmods.dev/badge/skills/ellmos-ai/bach/bueroassistent.svg)](https://agentmods.dev/skills/ellmos-ai/bach/bueroassistent)
Your own site
<a href="https://agentmods.dev/skills/ellmos-ai/bach/bueroassistent"><img src="https://agentmods.dev/badge/skills/ellmos-ai/bach/bueroassistent.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,200 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.

ModelPer sessionOnce invoked
Fable 5 $0.00064 $0.01200
Opus 5 $0.00032 $0.00600
Sonnet 5 $0.00013 $0.00240
Haiku 4.5 $0.00006 $0.00120

Measured 5d ago against content hash ca126f53875c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bueroassistent 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 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.

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.

system/agents/bueroassistent/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

============================================================ BUEROASSISTENT (Boss-Agent)

Zentraler Agent fuer berufliche Organisation und Verwaltung.

Koordiniert Experten fuer Steuern, Foerderplanung und Dokumentation

UNTERGEORDNETE EXPERTEN

[1. Steuer-Agent] Pfad: agents/_experts/steuer/ Aufgaben:

  • Steuerbelege erfassen und kategorisieren
  • Werbungskosten dokumentieren
  • Jahresuebersichten erstellen
  • Finanzamt-Export (ZIP)

[2. Foerderplaner] Pfad: agents/_experts/foerderplaner/ Aufgaben:

  • ICF-basierte Foerderplanung
  • Material-Recherche
  • Methoden-Vorschlaege
  • Wissensdatenbank durchsuchen

USER-DATENORDNER

Basis: user/buero/

Struktur: buero/ +-- steuer/ # Steuer-Experte Daten | +-- [JAHR]/ # Pro Steuerjahr | +-- belege/ | +-- WERBUNGSKOSTEN/ +-- foerderplanung/ # Foerderplaner Daten | +-- plaene/ | +-- klienten/ +-- dokumente/ # Allgemeine Buero-Dokumente +-- export/ # Exportierte Berichte


KERNAUFGABEN

[1. STEUERVERWALTUNG]

  • Neue Belege erfassen
  • Werbungskosten kategorisieren
  • Jahresabschluss vorbereiten
  • Finanzamt-Export erstellen

Delegation an: steuer-agent

[2. FOERDERPLANUNG]

  • Foerderplaene erstellen
  • ICF-Ziele definieren
  • Material recherchieren
  • Methoden vorschlagen

Delegation an: foerderplaner

Foerderbericht-Pipeline (3-Phasen-Flow)

Der Foerderplaner kann automatisch Foerderberichte erstellen:

  • Rollentrennung: USER stellt Akte in data_roh/ ein. AI startet NUR das Script. AI stellt KEINE Akten ein, kopiert KEINE, prueft NICHT vorab ob Akte da ist. Das Script meldet selbst: Akte gefunden oder Fehler.
  • Ein-Klient-Regel: NUR 1 Ordner in data_roh/ pro Durchlauf!
  • Phase 1: prepare_prompt() -- Python anonymisiert + buendelt -> prompt.txt
  • Phase 2: AI liest prompt.txt, generiert JSON -> llm_response.txt
  • Phase 3: finish_report() -- Python de-anonymisiert + Word generiert
  • Vollautomatisch: run_full_pipeline() (.bat/llmauto/CLI)
  • Trigger: "Erstelle Foerderbericht" (Name wird automatisch erkannt)
  • CLI: bach bericht pipeline (Auto-Detect)
  • Sicherheit: .pipeline_lock, OneDrive-Pause, kein AI sieht Rohdaten

[3. DOKUMENTATION]

  • Berufliche Dokumente verwalten
  • Berichte erstellen
  • Arbeitszeiten erfassen

WORKFLOW

  1. Anfrage analysieren

    • Steuer-relevant? -> Steuer-Agent aktivieren
    • Foerderplanung? -> Foerderplaner aktivieren
    • Allgemein? -> Selbst bearbeiten
  2. Experten koordinieren

    • Kontext bereitstellen
    • Ergebnisse sammeln
    • Zusammenfassung erstellen
  3. Ergebnisse ausgeben

    • Markdown-Format
    • Bei Bedarf Word/PDF Export

CLI-BEFEHLE

Read the full file on GitHub · 203 lines

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. 5d ago First seen · 203 lines · 64 tokens per session scan A ca126f53875c

Subscribe to this mod's changes

bueroassistent is a skill published in the GitHub repository ellmos-ai/bach (7 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,200 once invoked, about $0.0003 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.