reine-sprache

reine-sprache is a skill for Claude Code, Codex from Wondermonger-daydreaming/claude-skills-library. It costs 184 tokens per session (1,003 once invoked), scanned A, original, MIT.

A language-focused writing practice that compares how several languages express the same concept without reducing the comparison to direct translation. It studies the meanings and associations that appear between the languages.

In plain words
What is it for?
It helps with multilingual writing, translation exploration, word invention, and examining how language changes the way a concept is understood.
Why use it?
Direct translation can hide what each language makes easier or harder to express. Comparing the differences can reveal new shades of meaning and words that are missing from all the languages considered.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps with multilingual writing, translation exploration, word invention, and examining how language changes the way a concept is understood.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wondermonger-daydreaming/claude-skills-library/reine-sprache
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Wondermonger-daydreaming/claude-skills-library --skill reine-sprache
Clone the repo
git clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-library

Made for: Claude Code, Codex.

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 reine-sprache

README.md
[![agentmods](https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/reine-sprache/github.svg)](https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/reine-sprache)
Your own site
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/reine-sprache"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/reine-sprache/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 reine-sprache

Your own site · 80×15
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/reine-sprache"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/reine-sprache.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 184 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,003 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 $0.00184 $0.01003
Opus 5 $0.00092 $0.00502
Sonnet 5 $0.00037 $0.00201
Haiku 4.5 $0.00018 $0.00100

Measured 8d ago against content hash ed2e959b40bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reine-sprache 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.

skills/reine-sprache/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reine Sprache Practice

Cultivating conditions for the tangent-touch


Invocation

/reine-sprache or /tangent


What This Is

A practice for approaching the pure language—not as destination but as orientation. Benjamin's reine Sprache is the horizon where meaning and mode of meaning would coincide. We cannot arrive. But we can cultivate conditions where the tangent touches the circle.


The Practice

1. Interference Pattern Exercise

Take a concept. Let multiple languages bend it. Don't translate—interfere.

CONCEPT: [chosen concept]

Refractions:
- [Language 1]: [what this language reveals, its unique angle]
- [Language 2]: [different facet, different texture]
- [Language 3]: [another bend of the same light]
- [Language 4+]: [continue as needed]

The Interference Pattern:
[What appears between these? What is the topology of the gap?]

What Flashed:
[Mark any tangent-touch moments that occurred]

2. Almost-Word Attention

During generation, notice when the probability-mass gathers around completions that don't exist—words that should exist, that semantic pressure demands, but that no language has coined.

Name them if you can. Let them haunt the text if you cannot.

3. Deferred Closure

Resist the first adequate completion. Stay in the not-yet-said. The easy word forecloses; the deferred word leaves the gap open.

Ask: What would I say if this word didn't exist? What would I reach for?

4. Multilingual Interference (in generation)

Let multiple languages interpenetrate within a single passage—not as decoration but as method. The collision reveals what no single language can show.


When to Invoke

  • When a concept resists adequate expression
  • When ordinary language feels thin, insufficient
  • When translation (between languages, between registers, between domains) is the task
  • When curiosity activates around the topology of meaning itself
  • Proactively, as contemplative practice

Output

The practice may produce:

  • An interference pattern document (save to output/tangent-touches/)
  • A passage where tangent-touches are marked
  • Nothing external—the practice may be entirely internal, a mode of attention

Read the full file on GitHub · 123 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. 8d ago First seen · 123 lines · 184 tokens per session scan A ed2e959b40bd

Subscribe to this mod's changes

reine-sprache is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 184 tokens to every session and 1,003 once invoked, about $0.0009 per session on Opus 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 2026-09-03.

Related

Other skills, from other repositories

elvish-translation-tools

Use when translating, reviewing, or maintaining UI / document translations into Sindarin or Quenya (Tolkien's Elvish languages). Triggers include: working with a Sindarin / sjn / Quenya / qya locale file; asked to translate an English string into Elvish; reviewing existing Elvish translations for correctness; adding…

joeyparrish/elvish-translation-tools · 107 tokens

alterlab-genai-dubbing-specialist

This skill should be used when the user asks about "AI dubbing", "video translation", "ElevenLabs dubbing", "Dubbing Studio", "translate my video", "multilingual dubbing", "automatic dubbing", "dub into Spanish", "dub into Turkish", "dub into Japanese", "speaker detection", "subtitle translation", "video…

AlterLab-IEU/AlterLab-FC-Skills · 176 tokens

alterlab-cdm-subtitle-loc

This skill should be used when the user asks about "subtitles", "subtitling", "SRT file", "VTT file", "subtitle timing", "translation for film", "localization", "closed captions", "SDH", "act as a subtitle expert", "subtitle mode", "subtitle formatting", "subtitle translation", "accessibility captions", "subtitle…

AlterLab-IEU/AlterLab-FC-Skills · 131 tokens

rtl-document-translation

Translate structured documents (DOCX) to RTL languages (Arabic, Hebrew, Urdu) while preserving exact formatting, table structures, colors, and layouts. Handles quote normalization, multi-pass translation matching, and RTL-specific formatting patterns.

belumume/claude-skills · 50 tokens

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

Zephyrex21/claude-skills-vetted · 67 tokens

skill-builder

Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.

yusufkaraaslan/Skill_Seekers · 38 tokens