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 petar-djukic/writing-skills --skill accent-dialgit clone --depth 1 https://github.com/petar-djukic/writing-skillsWrote 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/petar-djukic/writing-skills/accent-dial)<a href="https://agentmods.dev/skills/petar-djukic/writing-skills/accent-dial"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/accent-dial/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/petar-djukic/writing-skills/accent-dial"><img src="https://agentmods.dev/badge/skills/petar-djukic/writing-skills/accent-dial.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 | $0.00000 | $0.02597 |
| Opus 5 | $0.00000 | $0.01299 |
| Sonnet 5 | $0.00000 | $0.00519 |
| Haiku 4.5 | $0.00000 | $0.00260 |
Grade A, and why
accent-dial 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 7d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: accent-dial description: >- Pre-terminal accent stage: dial a controllable amount of the author's Serbian-L1 accent into an article by accepting a ranked fraction of EN→Serbian→EN round-trip translation edits. One cached round-trip per article (gemma4:31b-cloud), paragraphs aligned 1:1, mechanically gated (citations, numbers, locks, length), ranked by Serbian-ness (calques, then restructuring depth); --dial 0..1 applies the top fraction deterministically with a full edit log. Generative source, deterministic application: the run is not done until the applied paragraphs pass an entailment review. Triggers: accent dial, serbian accent, round-trip translation, dial the accent, more serbian, less serbian, translation laundering, L2 accent stage.
Accent Dial (pre-terminal stage)
The EN→SR→EN round-trip is the only measured source of the author's
Serbian-L1 accent: the regular published articles carry ZERO calques and
sit below the native exemplars on the L2 composite (paper-stash
writing-voice/l2-markers.yaml, v1.2), while the gemma round-trip of
Strategy Theatre measured +0.726 — and simultaneously produced the
strongest Pangram move ever recorded on that article (0.708 → 0.150
fraction_ai, all 27 citations intact). But a whole-text round-trip is
all-or-nothing: locked spans get paraphrased, quoted specimens drift from
their blockquotes, and confident mistranslations ride along.
This stage makes the accent a dial instead. The round-trip is a CANDIDATE
GENERATOR, not a transformation: every paragraph pair is gated
mechanically, the survivors are ranked by how much Serbian they carry, and
--dial p applies the best-ranked fraction. Application is deterministic
and prefix-monotone (edits applied at a lower dial stay applied at every
higher one), every candidate lands in the edit log with its gate verdict
and score, and unapplied paragraphs stay byte-identical to the input.
What ships with it
2 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.
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.
- 7d ago Changed · +25 lines 8db79adf35a1
- 12d ago First seen · 166 lines · 0 tokens per session scan A 0f7fc47a716d
accent-dial is a skill published in the GitHub repository petar-djukic/writing-skills (4 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,597 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 2026-08-31.
Other skills, from other repositories
punct-master
A punctuation checker and fixer focused mainly on Chinese text, with separate rules for prose, technical documents, bilingual writing, and social posts.
punct-polish
A Chinese punctuation checker and fixer for prose, technical documents, mixed Chinese-English text, and social media posts.
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.
humanize-mba-text
A Chinese-language rewriting tool for making AI-generated text sound more natural in the style of a Chinese MBA thesis. It focuses on practical, evidence-based, academically structured writing.
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.
humanizer-czech
Odstraň znaky AI-generovaného psaní z českého textu. Použij při editaci nebo revizi textu, aby zněl přirozeněji a lidštěji. Detekuje a opravuje 27 vzorců včetně: nafouklého významu, propagačního jazyka, anglického slovosledu, kalků, nominalizace, monotónního rytmu, nadužívání spojek, typických českých AI klišé…