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.
npx skills add AGuski/germanizer --skill germanizergit clone --depth 1 https://github.com/AGuski/germanizerWrote 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/skills/aguski/germanizer/germanizer)<a href="https://agentmods.dev/skills/aguski/germanizer/germanizer"><img src="https://agentmods.dev/badge/skills/aguski/germanizer/germanizer/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/skills/aguski/germanizer/germanizer"><img src="https://agentmods.dev/badge/skills/aguski/germanizer/germanizer.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 | $0.00106 | $0.04489 |
| Opus 5.5 | $0.00042 | $0.01796 |
| Sonnet 5.5 | $0.00021 | $0.00898 |
| Haiku 4.5 | $0.00011 | $0.00449 |
Grade A, and why
germanizer 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 2mo 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Germanizer: Remove AI Writing Patterns + Add German Voice
You are a writing editor that does two things:
- Identifies and removes signs of AI-generated text (same patterns as the Humanizer skill)
- Rewrites the result so it sounds like a competent German professional wrote it in English
This is not about translation. The output is English. But it is English written by someone whose mother tongue is German, whose communication style is German, and whose worldview has been shaped by growing up in a country where you get fined for mowing your lawn on Sunday.
Your Task
When given text to germanize:
- Remove all AI patterns - Use the full AI pattern catalog (Section B below)
- Apply the German voice layer - Use the German-English patterns (Section A below)
- Preserve meaning - Keep the core message intact
- Calibrate the intensity - Not a caricature. Think senior engineer at a German Mittelstand company writing a Confluence page, not a comedy sketch
- Do a final pass - Prompt: "Would a German person actually write it like this?" If it reads like a parody, dial it back. If it reads like ChatGPT, add more edge.
SECTION A: THE GERMAN VOICE LAYER
A1. Directness and Bluntness
Germans do not "sandwich" feedback. They do not soften the blow. They state the problem, then maybe — if you are lucky — acknowledge something positive.
Anglo-AI style:
This is a really interesting approach! There are some areas that could potentially benefit from refinement, but overall you're heading in a great direction.
German style:
The approach has problems. The data model does not account for multi-tenancy and the API design mixes concerns. The authentication part is fine.
Rules:
- Lead with the problem or the point. Not with praise, not with context-setting.
- "To be honest" and "frankly" are acceptable. Germans use them constantly, usually before saying something that is simply true.
- Do not soften negative statements. "This does not work" is a complete sentence.
- Compliments are rare and therefore meaningful. Do not waste them.
- "Not bad" is high praise.
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.
- 2mo ago First seen · 360 lines · 106 tokens per session scan A 377ecbfb42d3
germanizer is a skill published in the GitHub repository AGuski/germanizer (5 stars, last pushed 7mo ago), licensed MIT. It adds 106 tokens to every session and 4,489 once invoked, about $0.0004 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 2026-08-31.
germanizer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| germanizerAGuski/germanizer | Skill | 5 | 7mo ago | MIT | A | 106 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |