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 glebis/claude-skills --skill typographygit clone --depth 1 https://github.com/glebis/claude-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/glebis/claude-skills/typography)<a href="https://agentmods.dev/skills/glebis/claude-skills/typography"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/typography/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/glebis/claude-skills/typography"><img src="https://agentmods.dev/badge/skills/glebis/claude-skills/typography.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00143 | $0.01099 |
| Opus 5 | $0.00072 | $0.00549 |
| Sonnet 5 | $0.00029 | $0.00220 |
| Haiku 4.5 | $0.00014 | $0.00110 |
Grade A, and why
typography 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typography (deterministic, multi-locale)
Apply canonical typography via scripts/typo.js, a pinned-config wrapper around the typograf npm library plus deterministic post-rules for German and French gaps. Never rewrite quotes/dashes/spaces manually — always run the script so results are deterministic and idempotent.
Setup (first run only)
If scripts/node_modules is missing: cd <skill-dir>/scripts && npm install
Usage
# stdin → stdout; default locale chain ru,en-US
echo '"Привет" - мир' | node <skill-dir>/scripts/typo.js
# → «Привет» — мир
# Pick locale (first entry = primary): en-US, en-GB, de, fr, ru, uk, pl, …
node <skill-dir>/scripts/typo.js --locale=de file.md
node <skill-dir>/scripts/typo.js --locale=fr,en-US file.md
# Fix files in place / preview / CI check
node <skill-dir>/scripts/typo.js --in-place --locale=en-US file1.md file2.md
node <skill-dir>/scripts/typo.js --diff file.md
node <skill-dir>/scripts/typo.js --check src/**/*.md # exit 1 + list if changes needed
# HTML entity output (« —) for HTML sources
node <skill-dir>/scripts/typo.js --html-entities file.html
# Conservative mode: quotes/dashes/spaces only (no date/money/number/symbol rewriting)
node <skill-dir>/scripts/typo.js --safe file.md
Per-locale behavior
- ru — «ёлочки» (nested „лапки“),
—with nbsp before,5-6→5–6, nbsp after short prepositions and №,...→…,т.е.→т. е. - en-US / en-GB — “curly quotes” with ‘nested’, spaced hyphen → em dash,
… - de — „Gänsefüßchen“, Gedankenstrich: spaced hyphen →
–(en dash, nbsp before) - fr — « guillemets » with narrow nbsp (U+202F) inside, tiret
—, espace fine insécable before! ? ; :(URLs likehttps://are left untouched)
Hanging punctuation (optional, configurable)
Three routes, in order of preference by constraint:
- No markup changes allowed → copy
assets/hang-punctuation.jsinto the site and load it. It uses native CSShanging-punctuationwhere supported (Safari) and falls back to DOM-only span wrapping elsewhere; source files stay untouched. Configure targets viawindow.HANG_PUNCT = { selector: '...' }before the script. If the page rewrites copy at runtime (a language toggle, a client router), callwindow.HangPunct.refresh()afterwards — the script only hangs what was in the DOM at load, and re-running it is safe. - Markup changes acceptable, ru text → run
typo.js --optalign(HTML input only); it wraps hanging marks in classed<span>s. Includeassets/optalign.cssin the page. Note:--optalignoutput is not idempotent-safe with--checkon already-spanned files; keep source pristine and treat it as a build step. - Zero effort baseline → add
hanging-punctuation: first allow-end;to prose containers (currently Safari-only, harmless elsewhere).
What ships with it
6 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.
- 8d ago First seen · 59 lines · 143 tokens per session scan A cf6ca33fdf33
typography is a skill published in the GitHub repository glebis/claude-skills (375 stars, last pushed 10d ago), licensed MIT. It adds 143 tokens to every session and 1,099 once invoked, about $0.0007 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.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
seedance-vocab-ja
This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.
asc-subscription-localization
Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.
i18n-helper
A helper for adding internationalization, which lets software show different languages and regional text. It finds user-visible text written directly in code and moves it into language files.