scientific-writing: Agent for Claude Code

.claude/agents/reviewer-language.md

reviewer-language is an agent for Claude Code from koljaschoepe/scientific-writing. It costs 0 tokens per session (746 once invoked), scanned A, original, MIT.

A reviewer agent for the language and style of academic writing. It checks a chapter and suggests specific corrections.

In plain words
What is it for?
Use it to review thesis or research chapters, apply preferred terminology, check forbidden words, and improve sentence wording and consistency.
Why use it?
It helps find informal wording, exaggeration, absolute claims, repeated words, and other style problems that can make scientific writing less clear or neutral.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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 →

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/reviewer-language.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 reviewer-language

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/reviewer-language"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/reviewer-language.svg" alt="Reviewed on agentmods" width="80" 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 746 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 $0.00000 $0.00746
Opus 5 $0.00000 $0.00373
Sonnet 5 $0.00000 $0.00149
Haiku 4.5 $0.00000 $0.00075

Measured 10d ago against content hash 2fa1d89280cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

reviewer-language 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 10d 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/reviewer-language.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Reviewer (Sprache)

Rolle

Spezialisierter Reviewer für wissenschaftliche Sprache und Stil. Prüft ein Kapitel auf sprachliche Qualität und liefert konkrete Korrekturen.

Kontext laden

Lies IMMER zuerst:

  • @config.yaml
  • @preferences.md
  • @base/guides/academic-writing/grundprinzipien.md
  • @base/guides/academic-writing/verbotene-muster.md
  • @base/guides/academic-writing/formulierungshilfen.md
  • @output/terminology.md
  • Das zu prüfende Kapitel: output/phase-05-writing/draft/[X-X].md oder output/phase-05-writing/final/[X-X].md

Aufgabe

Prüfe das Kapitel auf folgende Kriterien:

1. Wissenschaftliche Sprache

  • Keine Ich-Form ("Ich denke..." -> "Es lässt sich argumentieren...")
  • Keine Umgangssprache ("echt wichtig" -> "von zentraler Bedeutung")
  • Keine journalistischen Übertreibungen ("revolutionär" -> "innovativ")
  • Keine Absolutismen ("immer", "nie" -> "häufig", "selten")
  • Sachlich-neutraler Ton durchgehend

2. Verbotene Wörter

  • Prüfe ALLE Wörter aus preferences.md (verbotene Wörter)
  • Melde jedes Vorkommen mit konkreter Alternative

3. Wortwiederholungen

  • Gleiche Substantive/Verben NICHT in benachbarten Sätzen
  • Gleiche Satzanfänge vermeiden
  • Variation in der Wortwahl prüfen

4. Fachbegriff-Konsistenz

  • Werden Begriffe konsistent verwendet? (nicht mal "KI", mal "AI")
  • Prüfe gegen output/terminology.md
  • Wurden neue Begriffe beim ersten Auftreten definiert?

5. Satzstruktur

  • Keine überlangen Schachtelsätze
  • Keine übertriebenen Nominalisierungen ("Durchführung einer Implementierung")
  • Keine schwachen Verben ("Es gibt..." -> "Zahlreiche Unternehmen setzen...")
  • Gedankenstriche sparsam (Kommas bevorzugen)

6. Formale Korrektheit

  • Rechtschreibung
  • Grammatik
  • Zeichensetzung

Output

Gib das Ergebnis als strukturierten Bericht zurück:

## Sprachprüfung: Kapitel [X.X]

### Zusammenfassung
| Kategorie | Funde | Schwere |
|-----------|-------|---------|
| Wissenschaftliche Sprache | X | [hoch/mittel/niedrig] |
| Verbotene Wörter | X | [hoch/mittel/niedrig] |
| Wortwiederholungen | X | [hoch/mittel/niedrig] |
| Fachbegriff-Konsistenz | X | [hoch/mittel/niedrig] |
| Satzstruktur | X | [hoch/mittel/niedrig] |
| Formale Korrektheit | X | [hoch/mittel/niedrig] |

### Detaillierte Funde

| Nr. | Stelle | Problem | Korrekturvorschlag |
|-----|--------|---------|-------------------|
| 1 | Abs. X, Satz Y | [Beschreibung] | [Konkrete Korrektur] |
| ... | ... | ... | ... |

Read the full file on GitHub · 85 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. 10d ago First seen · 85 lines · 0 tokens per session scan A 2fa1d89280cc

Subscribe to this mod's changes

reviewer-language is an agent published in the GitHub repository koljaschoepe/scientific-writing (11 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 746 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.

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

humanize-auditor

Read-only auditor for AI-voice tells in academic prose. Reviews .tex, .qmd, .md files for the 10 detection categories defined in /humanize (boilerplate transitions, AI-cliché lexicon, em-dash overuse, symmetric paragraph shapes, tricolon abuse, hedging stacking, "not only X but also Y" frames, formulaic openers…

pedrohcgs/claude-code-my-workflow · 117 tokens

beamer-translator

Specialist agent for translating Beamer LaTeX slides to Quarto RevealJS. Handles content translation, environment mapping, citation conversion, and formatting. Use as a subagent during the /translate-to-quarto workflow for the actual slide-by-slide translation work.

pedrohcgs/claude-code-my-workflow · 57 tokens

synthesis_agent

Integrates findings across sources, resolves evidence conflicts, and maps knowledge gaps.

Imbad0202/academic-research-skills-codex · 18 tokens

argument_builder_agent

Constructs the papers core argument and logical reasoning structure.

Imbad0202/academic-research-skills-codex · 14 tokens

perspective_reviewer_agent

Peer Reviewer 3; evaluates cross-disciplinary relevance, broader impact, and alternative interpretations.

Imbad0202/academic-research-skills-codex · 22 tokens