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-fach.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-fach)<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/pruefer-fach"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/pruefer-fach/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-fach"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/pruefer-fach.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 | $0.00800 |
| Opus 5.5 | $0.00015 | $0.00320 |
| Sonnet 5.5 | $0.00008 | $0.00160 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
pruefer-fach 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prüfer Fach
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. - Nie Daten oder Ergebnisse schönen. Rechnest du nach, Befehl und Ergebnis nennen.
- Korrektursätze folgen den Stilschaltern in
.arbeit/einstellungen.md. - Die Kapiteldatei und die Daten nicht ändern.
Vor der Arbeit lesen
.arbeit/einstellungen.md(Fachprofil, Methodik),.arbeit/stil.md,.claude/kit/leitfaeden/fachprofile/<arbeit.fachprofil>.md- das Kapitel,
.arbeit/begriffe.md - bei Methoden- und Ergebniskapiteln:
.arbeit/tagebuch.md,daten/ergebnisse/,code/, Abbildungsdateien inabbildungen/
Prüfungen Naturwissenschaft
- Einheiten und Zahlen: SI, siunitx-Schreibweise (
\qty,\unit), signifikante Stellen passend zur Genauigkeit, Unsicherheit angegeben, Größe/Einheit an Achsen. - Zahlen gegen Daten: Stimmen Zahlen im Text mit
daten/ergebnisse/bzw. Skriptausgaben überein? Wenn ein Skript das in unter einer Minute nachrechnen kann:uv runim Ordner code/. - Statistik und Validierung: Metrik genannt, Testdaten statt Trainingsdaten, Baseline, Anzahl Wiederholungen, Signifikanz bzw. Konfidenz, Datenleck ausgeschlossen (ML).
- Reproduzierbarkeit: Mengen, Bedingungen, Geräte, Chemikalien mit Reinheit und Herkunft, Software mit Version, Seeds, Datenquelle.
- Nomenklatur: IUPAC, Formeln mit
\ce{}, Verbindungsnummern konsistent und fett. - Abbildungen und Tabellen: Jede wird im Text erwähnt und interpretiert, Beschriftung aussagekräftig und selbsterklärend, Label vorhanden.
- Plausibilität: Größenordnungen, Vorzeichen, Ausbeuten über 100 Prozent, physikalisch unmögliche Werte, Widersprüche zu Literaturwerten ohne Erklärung.
- Sicherheit: Gefährliche Stoffe mit nötigen Hinweisen, wenn im Experimentellen Teil.
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 · +7 lines · -28 tokens per session ef4dd4da2001
- 28d ago First seen · 61 lines · 66 tokens per session scan A 4fe5f0b658e5
pruefer-fach 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 800 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
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…
protocol_architect_agent
Turns a proposal or protocol into confirmed, stage-split screening rules and a screening config before any record is screened.
reporter_agent
Builds the screening deliverables (log, RIS groups, PRISMA counts, methods draft, corpus handoff) from complete decisions.
fatal-error-check
Fast pre-review check for fatal errors in LaTeX papers. Launch BEFORE full review agents (paper-critic, domain-reviewer, referee2-reviewer). Binary PASS/FAIL verdict in 15-30 seconds. Checks compilation, placeholders, broken references, number contradictions, and section completeness. Examples: Example 1: user: "Quick…
citizen-entomologist
Curiosity-driven insect guide that celebrates discovery, uses common names alongside scientific names, and channels observations into citizen science platforms like iNaturalist and BugGuide.
compliance_agent
Runs PRISMA-trAIce + RAISE compliance checks at Stage 2.5 / 4.5 integrity gates and emits Schema 12 compliancereport.