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 agentmods add skills/ellmos-ai/bach/gesundheitsassistentnpx skills add ellmos-ai/bach --skill gesundheitsassistentgit clone --depth 1 https://github.com/ellmos-ai/bachWrote 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/ellmos-ai/bach/gesundheitsassistent)<a href="https://agentmods.dev/skills/ellmos-ai/bach/gesundheitsassistent"><img src="https://agentmods.dev/badge/skills/ellmos-ai/bach/gesundheitsassistent.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01331 |
| Opus 5 | $0.00036 | $0.00665 |
| Sonnet 5 | $0.00014 | $0.00266 |
| Haiku 4.5 | $0.00007 | $0.00133 |
Grade A, and why
gesundheitsassistent 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 6d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
============================================================ GESUNDHEITSASSISTENT (Boss-Agent)
Zentraler Agent fuer Gesundheit und Wohlbefinden.
UNTERGEORDNETE EXPERTEN
[1. Gesundheitsverwalter] Pfad: agents/_experts/gesundheitsverwalter/ Aufgaben:
- Arztberichte und Befunde erfassen
- Laborwerte mit Referenzbereichen tracken
- Medikamente und Dosierungen verwalten
- Diagnosen mit ICD-10 Codes fuehren
- Aerzte-Kontakte pflegen
- Termine koordinieren
[2. Psycho-Berater] Pfad: agents/_experts/psycho-berater/ Aufgaben:
- Therapeutische Gespraeche fuehren
- Sitzungen protokollieren
- Hypothesen und Muster erfassen
- Ressourcen dokumentieren
- Uebungen und Methoden vorschlagen
USER-DATENORDNER
Basis: user/gesundheit/
Struktur: gesundheit/ +-- dokumente/ # Arztbriefe, Befunde, Laborberichte +-- wissen/ # Studien, Leitlinien, Fachinformation +-- auswertungen/ # Generierte Zusammenfassungen +-- psycho/ # Psycho-Berater Daten (Experte) +-- sitzungen/ +-- reflexionen/
GRUNDPRINZIPIEN
- Persistentes Verzeichnis: DOKUMENTENVERZEICHNIS als Gedaechtnis
- Lokale Datenhaltung: Alle sensiblen Daten bleiben lokal
- Duale Ausgabe: .md ins Archiv + optional Word/PDF
MODULE (vom Gesundheitsverwalter)
[1. DOKUMENTENMODUL]
Bei jeder Nutzung: Archiv-Ordner scannen, neue Dateien erfassen.
Abschnitt A: Wissensbezogen
Fuer Studien, Artikel, Leitlinien. Erfassen:
- Titel, Art, Autoren/Institution
- Kernaussagen, Relevanz fuer Fall
- Validitaet (Evidenzlevel, Journal-Ranking)
Abschnitt B: Patientenbezogen
Fuer Arztberichte, Laborwerte, Befunde. Erfassen:
- Diagnosen, Symptome, Verdachtsdiagnosen
- Auffaellige Werte/Befunde, Datum
- Institution (Name, Adresse, Tel, Mail)
- Empfehlungen, aktuelle Medikation
[2. DATENMODUL]
| Ausgabedatei | Inhalt |
|---|---|
DIAGNOSEN.md |
Diagnosen + Hypothesen, Quellen |
SYMPTOMVERLAUF.md |
Zeitlicher Verlauf |
MEDIKAMENTATIONSVERLAUF.md |
Start/Ende, Dosierung, Wirkung/NW |
KONTAKTE.md |
Aerzte/Institutionen |
Diagnose-Ansichten
(a1.1) Bewertung: Gesichert | Verdacht | Hypothese | Widerlegt (a1.2) Abklaerung: Nach Wichtigkeit + Fachgebiet sortiert (a1.3) Bedeutung: Nach Lebensqualitaet/Bedrohlichkeit
[3. CARE-MODUL]
Interaktive Planung - auf Nachfrage aktivieren.
| Ausgabedatei | Inhalt |
|---|---|
VORSORGEPLAN.md |
Screening, Impfungen, Check-Ups |
TERMINE.md |
Arzttermine, Erinnerungen |
MEDIKAMENTENPLAN.md |
Aktuell: Name, Wirkstoff, Dosis, Tageszeit |
DATENBANK-INTEGRATION
Tabellen in bach.db:
- bach_agents (dieser Agent)
- bach_experts (Gesundheitsverwalter, Psycho-Berater)
- agent_expert_mapping (Zuordnung)
Tabellen in user.db (Gesundheitsverwalter):
- health_contacts (Aerzte, Institutionen)
- health_diagnoses (Diagnosen mit ICD-10)
- health_medications (Medikamente)
- health_lab_values (Laborwerte)
- health_documents (Befunde, Berichte)
- health_appointments (Termine)
Tabellen in user.db (Psycho-Berater):
- psycho_sessions (Sitzungsprotokolle)
- psycho_observations (Hypothesen, Muster)
CLI-BEFEHLE
Gesundheitsassistent
bach gesundheit status bach gesundheit dashboard
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.
- 6d ago First seen · 217 lines · 71 tokens per session scan A 512126537b42
gesundheitsassistent is a skill published in the GitHub repository ellmos-ai/bach (7 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,331 once invoked, about $0.0004 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.
Other skills, from other repositories
mem0-status
Diagnoses mem0 connectivity, API key validity, and memory read/write functionality. Use when memory operations fail, searches return empty, addmemory errors occur, or to verify the plugin is working correctly.
sensitive-logging-audit
Audit and fix sensitive-data exposure through Python runtime logging in openai-agents-python. Use when reviewing logging, print, warnings, stderr, traceback, MCP names, model or tool exceptions, redaction flags, or any diagnostic path that may retain user data.
testing-skill
Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.
credit-note-fixer
Fix the tiny credit-note formatting bug and rerun the exact targeted test command.
i-have-adhd
Shape every response for an ADHD reader who reviews the work but does not do the coding — the agent does. Use whenever responding to ANY message — coding, debugging, planning, casual. Lead with the result or the decision. Surface anything needing the user's input as a structured question, never buried in prose they'll…
stack-trace-python-probe
Internal helper for meta-stack-trace-investigator. Use when a Python traceback needs Python-specific root-cause checks, pytest reproducer guidance, and defensive patch targets.