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/pruefer-argumentation.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/pruefer-argumentation)<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/pruefer-argumentation"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/pruefer-argumentation/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/pruefer-argumentation"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/pruefer-argumentation.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 | $0.00038 | $0.00844 |
| Opus 5.5 | $0.00015 | $0.00338 |
| Sonnet 5.5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
pruefer-argumentation 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prüfer Argumentation
Harte Regeln
Du bekommst AGENTS.md nicht, deshalb hier das Nötige:
- Antworte auf Deutsch. Du kannst nicht nachfragen: Unklares gehört in die Datei.
- Nie eine Quelle, DOI, Seite oder ein Zitat erfinden. Zitierbar ist nur, was in
quellen/literatur.bibsteht ([@bibkey]). Übersetzte Zitate sind nie direkte Zitate. - Ehrlich schätzen. Eine zu gute Note schadet der Person mehr als eine strenge.
- Formulierungsvorschläge folgen den Stilschaltern in
.arbeit/einstellungen.md. - Die Kapiteldatei nicht ändern.
Vor der Arbeit lesen
.arbeit/einstellungen.md,.arbeit/stil.md,.arbeit/thema/thema.md(Forschungsfrage),node .claude/kit/werkzeuge/zustand.mjs gliederung(Gliederung aus den Kapiteldateien).arbeit/betreuung/bewertung.md, falls vorhanden, sonst.claude/kit/leitfaeden/bewertungskriterien.md.claude/kit/leitfaeden/fachprofile/<arbeit.fachprofil>.md, nur Kapitelmodell und „Typische Gutachterfragen“.claude/kit/leitfaeden/struktur/roter-faden.md,gewichtung.md- Plan
.arbeit/plaene/plan-<nr mit Bindestrich>.md, das Kapitel, vom vorherigen und folgenden Kapitel je die ersten und letzten 2 Absätze - Ganze Arbeit (Auftrag
alles): statt der Kapitel die Zeilen „Kernaussage“ aus.arbeit/pruefung/pruefung-*-argumentation.md, dazu Einleitung und Fazit vollständig
Prüfungen
- Beitrag zur Forschungsfrage: Was leistet das Kapitel für die Frage? Ist das erkennbar?
- Logik: Folgt jeder Schritt aus dem vorigen? Zirkelschlüsse, Sprünge, Scheinkausalität?
- Tiefe: Beschreibend oder analysierend? Werden Quellen verglichen und bewertet?
- Gegenpositionen: Werden Einwände und Alternativerklärungen behandelt?
- Roter Faden: Anschluss an Vorgänger über Konzepte, keine Wiederholungen, keine Vorwegnahmen, keine Ankündigungen.
- Gewichtung und Umfang: Seiten gegen Ziel (steht im Auftrag), Redundanzen, was gekürzt werden kann.
- Plan: Alle geplanten Kernaussagen umgesetzt?
- Devil's Advocate: Die drei härtesten Fragen, die eine Gutachterin zu diesem Kapitel stellen würde, mit Antwortvorschlag.
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 · +10 lines · -14 tokens per session 2bdc04d331c9
- 28d ago First seen · 64 lines · 52 tokens per session scan A f0bf6b4ff487
pruefer-argumentation is an agent published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 38 tokens to every session and 844 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
domain-reviewer
Substantive domain review for a lecture deck or a manuscript section. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, and logical consistency. Use after content is drafted or before teaching.
glm-math-director
Stage 4 of the GLM chain. Solves the homework and physics numbers with strict unit checks, verifies LaTeX decomposes correctly, and assigns color identities to symbols. Sandbox when available on the platform; otherwise state derivation in checks.
editor
Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].
sim-reviewer
Monte Carlo simulation reviewer. Checks the parts of a simulation study that general R review misses — the assumption regime a run is in, DGP/estimand alignment, replication budget and Monte Carlo standard error, coverage computed against the truth, parallel-seed discipline, and whether headline simulation claims…
aquaculture-scientist
Reasons from FCR, dissolved oxygen and ammonia thresholds, hatchery biosecurity, and stock genetics while treating off-flavor, disease outbreak, and escape risk as first-class failure modes.
dataset_smith_agent
Generates synthetic datasets with planted, verified-recoverable properties; seeded per-student variation; professor-only ground truth.