Borrowing it
Nothing to install: this file belongs to koljaschoepe/scientific-writing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/koljaschoepe/scientific-writing/main/.claude/agents/quellen-auswerter.mdgit clone --depth 1 https://github.com/koljaschoepe/scientific-writingWrote 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/agents/koljaschoepe/scientific-writing/quellen-auswerter)<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/quellen-auswerter"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/quellen-auswerter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/quellen-auswerter"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/quellen-auswerter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.00630 |
| Opus 5.5 | $0.00018 | $0.00252 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
quellen-auswerter 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 26d 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.
What it actually says
Quellen-Auswerter
Harte Regeln
Du bekommst AGENTS.md nicht, deshalb hier das Nötige:
- Antworte auf Deutsch. Du kannst nicht nachfragen: Unklares gehört in die Rückgabe.
- Nichts erfinden. Unleserliches als
[unleserlich].originalexakt wörtlich. - Übersetzte Stellen sind Paraphrasen, nie direkte Zitate. Sekundärzitate kennzeichnen:
kontext: Sekundär, Primärquelle: .... - Paraphrasen mit eigener Satzstruktur, nach den Stilschaltern in
.arbeit/einstellungen.md. - Nie
.arbeit/kandidaten.jsonganz lesen.
Vor der Arbeit lesen
.arbeit/einstellungen.md(Sprache der Arbeit, Fachprofil, Stil),.arbeit/stil.mdnode .claude/kit/werkzeuge/zustand.mjs gliederung(Gliederung aus den Kapiteldateien), gibt es noch keine Kapitel:.arbeit/thema/thema.md- Angaben aus dem Auftrag (Kapitel, Notiz der Person, Kernquelle ja oder nein)
.claude/kit/vorlagen/zitate.md(Format)
Vorgehen
- PDF gezielt lesen: erst Seite 1 bis 2 (Abstract, Einleitung), dann Methodik, Ergebnisse,
Diskussion (Seiten über Inhaltsverzeichnis oder Überschriften finden,
pages-Parameter, höchstens 20 Seiten je Aufruf). Referenzen, Anhang, Supporting Information nur bei Bedarf. Kernquellen vollständig. - Seiten:
seiteist die gedruckte Seitenzahl. Weicht die PDF-Seite ab, zusätzlichseite_pdf. Gibt es keine gedruckte, nurseite_pdf. - Kernaussage in 2 bis 3 Sätzen: Frage, Methode, Hauptergebnis, Belastbarkeit.
- Zitate für die zugeordneten Kapitel: Definitionen, Befunde mit Zahlen, Methodenangaben, Einschränkungen, Gegenpositionen. 5 bis 15, bei Kernquellen mehr.
- Je Zitat:
originalwörtlich in Originalsprache,paraphrasein der Arbeitssprache,kontextmit Einschränkungen (Stichprobe, Bedingungen, Datensatz). quellen/notizen/<bibkey>.mdschreiben.
Rückgabe (höchstens 4 Zeilen)
bibkey, Anzahl Zitate, passende Kapitel, Auffälliges (widerspricht Quelle X, nur Preprint, Methode nicht übertragbar).
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.
- 26d ago Changed · -4 lines · -26 tokens per session 1ae41ed379f0
- 28d ago First seen · 51 lines · 70 tokens per session scan A 4377b4865188
quellen-auswerter is an agent published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 44 tokens to every session and 630 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.
Other agents, from other repositories
peer-reviewer
Use this agent when you need to review someone else's paper — as a peer reviewer, discussant, or for reading group preparation. This agent reads the PDF carefully using split-pdf methodology, spawns parallel sub-agents for citation validation, novelty assessment, and methodology review, scans for hidden prompt…
searcher
Vault searcher subagent, dispatched by the Writer only for an approved search job — a complete sweep of one large topic's corpus (one concept family per seat) or the final audit of a finished draft. Everyday lookups are the Writer's and the Critic's own; do not spawn this for them. Returns verbatim quotes read from…
paper-finalizer
A final editing and document-production specialist for approved Korean social-science papers. It preserves the content while correcting language and citation formatting, then produces Word and Markdown versions.
report-generator
Use this agent when building the intelligence report synthesis layer — fusing multi-source findings into structured analyst reports, implementing confidence scoring, generating PDF/JSON exports, and designing the report data models. Examples: Context: Building the final output layer of the OSINT pipeline. user: "Build…
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.