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/helpnpx skills add ellmos-ai/bach --skill helpgit clone --depth 1 https://github.com/ellmos-ai/bachWhat 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 | $0.00054 | $0.01353 |
| Opus 5 | $0.00027 | $0.00677 |
| Sonnet 5 | $0.00011 | $0.00271 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade A, and why
help-forensik 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 2d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help-Forensik Service
Kategorie: Qualitaetssicherung & Dokumentation Recurring: help_forensic (alle 14 Tage)
Zweck
Systematische Ueberpruefung der Help-Dokumentation auf Aktualitaet. Vergleicht dokumentierten Soll-Zustand mit tatsaechlicher Implementierung und aktualisiert entweder Help oder Roadmap.
Trigger
Automatisch (Recurring Task)
- Intervall: 14 Tage
- Task: "Help-Forensik: Eine docs/help/*.txt pruefen..."
- Ziel: Dokumentation immer aktuell halten
Manuell
- Nach groesseren Code-Aenderungen
- Bei Nutzer-Meldung "Doku stimmt nicht"
- Nach Implementierung von Roadmap-Tasks
Ereignis-basiert
- CLI-Handler geaendert (hub/*.py)
- Neuer Befehl hinzugefuegt
- Feature-Implementierung abgeschlossen
Workflow (Kurzfassung)
1. HELP-DATEI AUSWAEHLEN
└─> Zufaellig aus docs/help/*.txt
└─> Oder nach Auftrag spezifisch
└─> Priorisierung: aelteste zuerst
2. DOKUMENTIERTEN ZUSTAND ERFASSEN
└─> Beschriebene Befehle extrahieren
└─> Beschriebene Funktionen notieren
└─> Beschriebene Dateipfade merken
3. FORENSISCHE UNTERSUCHUNG
└─> Befehle testen (bach --help X)
└─> Code pruefen (hub/)
└─> Pfade verifizieren
└─> Funktionen aufrufen
4. ABWEICHUNGEN KLASSIFIZIEREN
┌─> VERBESSERUNG: System besser als dokumentiert
│ └─> Help aktualisieren
│ └─> CHANGELOG Eintrag
│
└─> ZIELZUSTAND NICHT ERREICHT: Feature fehlt
└─> In Tasks/Roadmap pruefen
└─> Wenn nicht geplant: Hinzufuegen
└─> Status dokumentieren
5. KONTEXT-RECHERCHE (bei Zweifeln)
└─> ROADMAP.md pruefen
└─> Tasks-Tabelle pruefen
└─> Logs durchsuchen
└─> Memory/Sessions lesen
6. AKTION DURCHFUEHREN
└─> Help anpassen ODER
└─> Roadmap/Tasks erweitern
└─> Analysebericht speichern
└─> CHANGELOG aktualisieren
Analyse-Schema (standardisiert)
HELP-FORENSIK ANALYSEBERICHT
============================
Datum: YYYY-MM-DD
Datei: docs/help/[name].txt
Letzte Aenderung: [Datum der Datei]
DOKUMENTIERTER ZUSTAND
----------------------
Befehle: [Liste der beschriebenen Befehle]
Funktionen: [Liste der beschriebenen Features]
Pfade: [Referenzierte Dateien/Ordner]
FORENSISCHE BEFUNDE
-------------------
| Befehl/Feature | Dokumentiert | Tatsaechlich | Status |
|----------------|--------------|--------------|--------|
| bach --X | Ja | Funktioniert | OK |
| bach --Y | Ja | Fehlt | LUECKE |
| bach --Z | Nein | Existiert | NEU |
ABWEICHUNGEN
------------
1. [Beschreibung der Abweichung]
Klassifikation: [VERBESSERUNG | ZIELZUSTAND_FEHLT]
Begruendung: [Warum diese Klassifikation]
DURCHGEFUEHRTE AKTION
---------------------
[ ] Help aktualisiert: [Details]
[ ] Roadmap erweitert: [Task-ID]
[ ] CHANGELOG Eintrag erstellt
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.
- 2d ago First seen · 191 lines · 54 tokens per session scan A b65899141f8b
help-forensik is a skill published in the GitHub repository ellmos-ai/bach (7 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 1,353 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.
Other skills, from other repositories
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.
wiki-lint
Run a deterministic, read-only health check on an Obsidian wiki. Use for lint, vault health check, audit wiki health, find orphans, find dead links, frontmatter audit, provenance audit, or wiki audit. Reports graph, link, frontmatter, provenance-ledger, empty-section, and stale-index findings; it does not reason…
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
research-mode
Anti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…