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/wikinpx skills add ellmos-ai/bach --skill wikigit 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/wiki)<a href="https://agentmods.dev/skills/ellmos-ai/bach/wiki"><img src="https://agentmods.dev/badge/skills/ellmos-ai/bach/wiki.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 | $0.00045 | $0.01131 |
| Opus 5 | $0.00023 | $0.00566 |
| Sonnet 5 | $0.00009 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
wiki-autoren 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki-Autoren Service
Kategorie: Dokumentation & Wissen Recurring: wiki_author (alle 21 Tage)
Zweck
Automatische Erweiterung, Aktualisierung und Qualitaetssicherung der
Wiki-Wissensbasis in wiki/.
Der Service hat drei Hauptaufgaben:
- ERSTELLEN - Neue Artikel basierend auf Agenten/Experten-Bedarfen
- AKTUALISIEREN - Bestehende Artikel auf Aktualitaet pruefen
- VALIDIEREN - Fakten durch Stichproben verifizieren
Modi
Modus A: Neuen Artikel erstellen
Identifiziert Wissensluecken bei Agenten/Experten und erstellt gezielte Wiki-Beitraege durch Web-Recherche.
- Analysiert Agent-Profile (SKILL.md, manifest.json)
- Identifiziert fehlende Wissensartikel
- Recherchiert in Web, Wikipedia, Fach-Datenbanken
- Erstellt formatierten Wiki-Artikel
- Entscheidet: Einzelartikel oder Themenordner
Modus B: Artikel aktualisieren
Prueft bestehende Artikel auf Aktualitaet basierend auf Validierungsmetadaten.
- Findet Artikel mit faelliger Pruefung
- Verifiziert Quellen (noch erreichbar? aktuell?)
- Aktualisiert Inhalte bei Bedarf
- Erneuert Validierungsmetadaten
Modus C: Fakten-Stichprobe
Qualitaetssicherung durch Verifizierung einzelner Fakten.
- Waehlt zufaelligen Artikel
- Extrahiert 3-5 pruefbare Fakten
- Recherchiert jeden Fakt
- Bewertet Artikelqualitaet
- Empfiehlt Massnahmen
Trigger
Automatisch (Recurring Task)
- Intervall: 21 Tage
- Rotation: A → B → C → A → ...
- Task: "Wiki-Autoren: [Modus] durchfuehren..."
Manuell
- Bei Erstellung neuer Agenten/Experten
- Bei Identifikation von Wissenslucken
- Nach Nutzer-Anfrage zu fehlendem Wissen
Ereignis-basiert
- Neuer Agent in agents/ erkannt
- Nutzer fragt nach Thema das nicht in Wiki ist
- Agent meldet fehlendes Kontextwissen
Validierungsmetadaten
Jeder Wiki-Artikel sollte diese Metadaten haben:
# Portabilitaet: UNIVERSAL|SYSTEM|PRIVAT
# Zuletzt validiert: YYYY-MM-DD (Autor)
# Naechste Pruefung: YYYY-MM-DD
# Quellen: [URL1], [URL2]
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.
- 5d ago First seen · 181 lines · 45 tokens per session scan A 8e9e2be585a1
wiki-autoren is a skill published in the GitHub repository ellmos-ai/bach (7 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,131 once invoked, about $0.0002 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
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
adapter-authoring
Build a custom source → raw-intake adapter for Athenaeum. Use when someone wants to feed an external source (an API, an export file, a message feed, a scraper, another tool's output) into an Athenaeum knowledge base, asks "how do I write an adapter / integration for athenaeum", or wants to turn some data source into…
resolve-questions
Walk the user through unresolved entries in pendingquestions.md one at a time. Use when the SessionStart hook surfaces pending memory questions, when the user says "resolve pending questions" / "go through my questions" / "what questions do I have", or when the user wants to clear the contradiction queue.
obsidian-knowledge
Use for any knowledge work in an Obsidian vault — capturing a quick note or link, organizing an Inbox, or turning bigger material (PDFs, docx, slides, syllabi, papers, transcripts, URL lists) into structured, teaching-quality notes. Works for any subject, adapts to the vault it's in, and does as much or as little…
superbrain-recall
Search the user's SuperBrain second-brain vault. Use whenever the user references past work, prior decisions, "how did we", "did we already", earlier sessions, a project's history, or anything that may already be recorded — before answering from scratch.
knowledge-transfer
Interview a person and turn their operating know-how (tacit knowledge) into the company brain: processes, rules with source, a glossary, decisions and open questions, written into the workspace. Use whenever someone needs to capture how a process actually gets done, before a key person leaves or retires, to onboard a…