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 marmbiz/humanizer-de --skill humanizer-degit clone --depth 1 https://github.com/marmbiz/humanizer-deWrote 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/marmbiz/humanizer-de/humanizer-de)<a href="https://agentmods.dev/skills/marmbiz/humanizer-de/humanizer-de"><img src="https://agentmods.dev/badge/skills/marmbiz/humanizer-de/humanizer-de/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/marmbiz/humanizer-de/humanizer-de"><img src="https://agentmods.dev/badge/skills/marmbiz/humanizer-de/humanizer-de.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 | $0.00054 | $0.05274 |
| Opus 5.5 | $0.00022 | $0.02110 |
| Sonnet 5.5 | $0.00011 | $0.01055 |
| Haiku 4.5 | $0.00005 | $0.00527 |
Grade A, and why
humanizer-de 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 22d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 434 B
- assets/banner-dark.svg 1.2 KB
- assets/banner-light.svg 1.2 KB
- assets/beispiel-durchlauf.svg 3.1 KB
- assets/checkliste-ki-tells.md 2.9 KB
- assets/humanizer-de-hero.png 1268 KB
- assets/humanizer-de-hero.webp 74 KB
- assets/social-preview.png 651 KB
- references/de-naturalness.md 9.3 KB
- references/decision-tables.md 15 KB
- references/evidence-ledger.md 7.3 KB
- references/patterns.md 115 KB
- references/qgir.md 2.7 KB
- references/quality-rubric.md 3.7 KB
- references/register-profiles.md 3.2 KB
- references/source-sweep.md 3.6 KB
- references/style-targets.json 382 B
- references/user-profile.md 2.2 KB
- scripts/bench.py 7.7 KB runs code
- scripts/build_skill_bundle.py 4.0 KB runs code
- scripts/cli_output.py 4.2 KB runs code
- scripts/detection_snapshot.py 6.0 KB runs code
- scripts/doctor.py 17 KB runs code
- scripts/evidence_lint.py 24 KB runs code
- scripts/fp_corpus_report.py 3.3 KB runs code
- scripts/german_pattern_lint.py 28 KB runs code
- scripts/humanizer_audit.py 20 KB runs code
- scripts/humanizer_two_pass.py 65 KB runs code
- scripts/register_lint.py 13 KB runs code
- scripts/rhythm_lint.py 20 KB runs code
- scripts/run_review_eval.py 12 KB runs code
- scripts/spell_lint.py 4.2 KB runs code
- scripts/style_profile.py 9.1 KB runs code
- scripts/syntax_lint.py 9.1 KB runs code
- scripts/text_scope.py 8.5 KB runs code
- scripts/unicode_lint.py 15 KB runs code
- scripts/verify_changes.py 5.5 KB runs code
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.
- 22d ago Changed 7b2d5f053468
- 25d ago Changed 68c2b3a24b82
- 1mo ago Changed · -1 lines 111a7a508d1f
- 1mo ago Changed ec6019584b05
- 1mo ago Changed 36a3efe65879
- 1mo ago Changed · +1 lines c1f3b88becb1
- 1mo ago Changed · +1 lines 4d01344ced29
- 1mo ago First seen · 176 lines · 54 tokens per session scan A 3f5098ca7457
humanizer-de is a skill published in the GitHub repository marmbiz/humanizer-de (185 stars, last pushed 23d ago), with no licence file. It adds 54 tokens to every session and 5,274 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 2026-08-30.
Other skills, from other repositories
humanizer-fr
Réécrit un texte français qui sonne IA pour qu'il se lise comme son auteur, sans changer ce qu'il dit. À utiliser pour relire ou réécrire de la prose en français : « pas X mais Y », chutes en une ligne, amorces mises en scène, triades forcées, tirets partout, portée gonflée, ton promotionnel, mots-béquilles, gras…
speak-human-tw
A Traditional Chinese editing guide for making public-facing writing sound more natural and less machine-generated. It also checks wording associated with Mainland China and half-width punctuation.
humanizer-ru
A Russian-text editor that removes bureaucratic wording, filler, copied chatbot patterns and signs of AI writing while keeping facts and examples.
turkce-humanizer
Türkçe metinlerden AI-üretimi yazım imzalarını temizler ve metnin registeri uygunsa insan Türkçesinin ritim imzalarını yerleştirir. "Türkçeleştir," "AI kokusunu at," "bu Türkçe metni doğallaştır," "humanize et" gibi ifadelerle veya AI-üretimi görünen Türkçe paragraf sunulduğunda tetiklenir.
humanizer-ko
A Korean-language editing guide for finding and removing writing patterns that can make text look AI-generated. It rewrites the text while keeping its original information and intended style.
unslop
Writing guardrail against AI slop in German and English. Apply automatically, without being asked, whenever you draft or revise prose that a person will send, post or publish and that runs longer than a few sentences: emails and replies, chat messages (Slack, Teams), LinkedIn and other social posts, software tickets…