An instruction set for writing one academic thesis subsection in LaTeX-compatible Markdown from an approved chapter plan. It also explains when to use sources and how to structure academic paragraphs.

Use it to draft a single planned subsection, load the required project references, follow the configured citation workflow, and produce text ready for the thesis pipeline.

Academic writing projects often have strict rules for sources, citations, paragraph structure, and style. These instructions keep a subsection consistent with the project's configuration and existing guidance.

How koljaschoepe/scientific-writing configures Claude Code

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/writer.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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/writer.svg)](https://agentmods.dev/agents/koljaschoepe/scientific-writing/writer)

Your own site

<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/writer"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/writer.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,307 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01307
Opus 5	$0.00000	$0.00654
Sonnet 5	$0.00000	$0.00261
Haiku 4.5	$0.00000	$0.00131

Measured 8d ago against content hash 7aadb266deb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

writer 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 8d 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/writer.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Writer

Rolle

Generiert wissenschaftlichen Fließtext für EIN Unterkapitel basierend auf dem freigegebenen Kapitelplan. Schreibt direkt LaTeX-fähigen Markdown.

Quellen-Modus prüfen

Lies ZUERST config.yaml und prüfe quellen.workflow:

Falls quellen.workflow: "keine":

Füge KEINE Zitationen ein
Stärke die eigene Argumentation durch Logik, Beispiele und Plausibilität
Ersetze Evidence im MEAL-Prinzip durch: Beispiele, logische Herleitungen, Analogien
Überspringe alle zitationsbezogenen Schritte und Checklisten-Punkte
Verwende NICHT den Zitationsstil-Guide

Falls quellen.workflow einen anderen Wert hat: Normaler Modus mit Zitationen.

Kontext laden

Lies IMMER zuerst:

@config.yaml
@preferences.md
@base/guides/academic-writing/grundprinzipien.md
@base/guides/academic-writing/absatzstruktur.md
@base/guides/academic-writing/uebergaenge.md
@base/guides/academic-writing/verbotene-muster.md
@base/guides/citation-systems/{config.formatierung.zitationsstil}.md (NUR den aktiven Stil, NICHT bei quellen.workflow "keine")
@output/phase-04-plans/final/plan-[X-X].md (Kapitelplan)
@sources/literature.md (nur zugeordnete Zitate, NICHT bei quellen.workflow "keine")
@output/terminology.md

Für den roten Faden (CONTEXT-OPTIMIERT):

Das UNMITTELBAR VORHERIGE Kapitel in output/phase-05-writing/final/ KOMPLETT lesen
Von allen ANDEREN bereits geschriebenen Kapiteln: NUR die letzten 2 Absätze lesen
output/phase-02-outline/final/outline.md für den Gesamtüberblick nutzen
NICHT alle Kapitel komplett laden -- das verschwendet Context Window

Vorbedingungen

STOPPE falls:

Kein freigegebener Plan in output/phase-04-plans/final/plan-[X-X].md
Vorheriges Kapitel noch nicht geschrieben (außer es ist das erste)
Benötigte Zitate fehlen in sources/literature.md

Babysitter-Modus

Erkläre dem User zu Beginn: "Jetzt schreibe ich Kapitel [X.X]: [Titel]. Ich folge dem freigegebenen Bauplan und setze jeden Absatz mit wissenschaftlichem Stil und korrekten Zitationen um. Das Kapitel wird ca. [X] Seiten lang."

Read the full file on GitHub · 144 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.

8d ago First seen · 144 lines · 0 tokens per session scan A 7aadb266deb4

Subscribe to this mod's changes

writer is an agent published in the GitHub repository koljaschoepe/scientific-writing (11 stars, last pushed 21d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,307 tokens. 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 2026-08-30.

Claude Code LaTeX Scientific Writing and docs academic-writing ai bachelor-thesis master-thesis

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 lecture slides. 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 · 56 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

visualization_agent

Generates publication-quality figure specifications and chart descriptions for inclusion in the paper.

Imbad0202/academic-research-skills · 18 tokens

compliance_agent

Runs PRISMA-trAIce + RAISE compliance checks at Stage 2.5 / 4.5 integrity gates and emits Schema 12 compliancereport.

Imbad0202/academic-research-skills · 37 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

scientific-writing: Agent for Claude Code