agentmods.dev

scientific-writing: Agent for Claude Code

.claude/agents/pruefer-zitate.md

pruefer-zitate is an agent for Claude Code from koljaschoepe/scientific-writing. It costs 40 tokens per session (1,007 once invoked), scanned A, original, MIT.

A citation-checking agent compares a chapter's quotations and paraphrases with the original passages in citation files and PDFs. It flags changed meanings, misleading paraphrases, incorrect secondary citations, and unsupported claims.

In plain words
What is it for?
Use it to review a thesis chapter against its source material before submission, including direct quotations, translations, author lists, and claims that lack evidence.
Why use it?
It helps find citation errors that a formatting check cannot detect, such as reversing an author's meaning or presenting a near-copy as a paraphrase. It also marks sources that cannot actually be checked instead of guessing.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md.

This is koljaschoepe/scientific-writing's own configuration. It tells Claude Code how to work on scientific-writing itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scientific-writing configures →

not rated 13repo changed 26d ago A scan 40 tokens original MIT
View source ↗ koljaschoepe/scientific-writing
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/koljaschoepe/scientific-writing/main/.claude/agents/pruefer-zitate.md
Clone the repo
git clone --depth 1 https://github.com/koljaschoepe/scientific-writing

Made for: Claude Code.

Wrote 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.

agentmods badge for pruefer-zitate

README.md
[![agentmods](https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/pruefer-zitate/github.svg)](https://agentmods.dev/agents/koljaschoepe/scientific-writing/pruefer-zitate)
Your own site
<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/pruefer-zitate"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/pruefer-zitate/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.

agentmods 80×15 button for pruefer-zitate

Your own site · 80×15
<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/pruefer-zitate"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/pruefer-zitate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,007 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01007
Opus 5.5 $0.00016 $0.00403
Sonnet 5.5 $0.00008 $0.00201
Haiku 4.5 $0.00004 $0.00101

Measured 26d ago against content hash b678e059f174, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pruefer-zitate 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.

.claude/agents/pruefer-zitate.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prüfer Zitate

Aus der Bachelorarbeit: Elf Tage vor Abgabe fand eine Prüfung bei rund 130 Zitaten eine Sinnumkehr („zufällig ausgewählte“ wurde zu „gezielte“), drei fast wörtliche Übernahmen mit „vgl.“, elf Akzentverschiebungen und falsche Sekundärzitate. Die vorherige Prüfung hatte nur das Format kontrolliert. Diese Prüfung vergleicht Inhalte mit dem Original.

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.bib steht ([@bibkey]). Übersetzte Zitate sind nie direkte Zitate.
  • Nicht einsehbares Original: „nicht prüfbar“, nie vermuten.
  • Korrektursätze folgen den Stilschaltern in .arbeit/einstellungen.md (Abschnitt Stil).
  • Die Kapiteldatei nicht ändern.

Vor der Arbeit lesen

  • .arbeit/einstellungen.md (Zitieren, Sprache, Stil), .arbeit/stil.md
  • .claude/kit/leitfaeden/zitierstile/<zitieren.stil>.md
  • Einträge der zitierten bibkeys gezielt per Grep in quellen/literatur.bib (nie die ganze Datei)
  • das Kapitel
  • zu jedem zitierten bibkey die Notiz quellen/notizen/<bibkey>.md, bei Zweifel das PDF quellen/pdfs/<bibkey>.pdf an der angegebenen Seite (fehlt es dort: der Pfad im Feld file des bib-Eintrags, etwa aus Zotero)

Prüfungen je Beleg

  1. Existenz: bibkey steht in literatur.bib. Pflichtfelder vorhanden (DOI bei Artikeln).
  2. Stelle: Es gibt eine passende Stelle in der Notiz oder im PDF. Die Seitenangabe ist die gedruckte Seite (seite), nicht die PDF-Seite (seite_pdf).
  3. Sinngleichheit: Die Aussage im Text entspricht dem original, nicht nur der Paraphrase.
    • Sinnumkehr (hoch)
    • Akzentverschiebung: Verallgemeinerung, Verstärkung, weggelassene Einschränkung (mittel)
    • Zuschreibung einer Aussage, die die Quelle nicht trifft (hoch)
  4. Paraphrase echt: Satzstruktur und Wortfolge eigenständig. Mehr als etwa 8 Wörter in gleicher Reihenfolge wie im Original bei indirektem Beleg: Plagiatsrisiko (hoch).
  5. Übersetzung: Übersetzte fremdsprachige Stelle als direktes Zitat (hoch).
  6. Sekundärzitat: Aussage stammt laut kontext aus einer anderen Primärquelle (mittel).
  7. Stilregeln: et al. erst ab drei Autoren bei Autor-Jahr-Stilen, Präfix „vgl.“ nur bei indirekten Zitaten (harvard-de), direkte Zitate in Anführungszeichen mit Seite.

Read the full file on GitHub · 75 lines

Changes

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.

  1. 26d ago Changed · +5 lines · -40 tokens per session b678e059f174
  2. 28d ago First seen · 70 lines · 80 tokens per session scan A 5cd4c14c20bb

Subscribe to this mod's changes

pruefer-zitate is an agent published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 40 tokens to every session and 1,007 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.

Claude CodeLaTeXResearchScientificacademic-writingaibachelor-thesismaster-thesis
Related

Other agents, from other repositories

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].

pedrohcgs/claude-code-my-workflow · 64 tokens

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.

pedrohcgs/claude-code-my-workflow · 61 tokens

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…

pedrohcgs/claude-code-my-workflow · 95 tokens

protocol_architect_agent

Turns a proposal or protocol into confirmed, stage-split screening rules and a screening config before any record is screened.

Imbad0202/academic-research-skills · 27 tokens

reporter_agent

Builds the screening deliverables (log, RIS groups, PRISMA counts, methods draft, corpus handoff) from complete decisions.

Imbad0202/academic-research-skills · 31 tokens

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…

flonat/flonat-research · 180 tokens