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 5.5 | $0.00057 | $0.00440 |
| Sonnet 5.5 | $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 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 — 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.
- 2mo ago First seen · 59 lines · 143 tokens per session scan A cf6ca33fdf33
typography is a skill published in the GitHub repository glebis/claude-skills (409 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 1,099 once invoked, about $0.0006 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 2026-09-03.
typography compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| typographyglebis/claude-skills | Skill | 409 | yesterday | MIT | A | 143 | Claude Code, Codex |
| global-data-get-{country}bobadilla-tech/requiems-api-skills | Skill | 2 | 1mo ago | MIT | A | 31 | Claude Code |
| global-data-post-resolvebobadilla-tech/requiems-api-skills | Skill | 2 | 1mo ago | MIT | A | 38 | Claude Code |
| detect-language-post-detect-languagebobadilla-tech/requiems-api-skills | Skill | 2 | 1mo ago | MIT | A | 32 | Claude Code |
| ios-appstore-release-managerflaqai/ios-application-development-skills | Skill | 5 | 2mo ago | MIT | A | 82 | Codex |
| pm-bilingualdannyhoang249-hub/pm-vietnamese-skill | Skill | 1 | 1mo ago | MIT | A | 53 | Codex |
| cm-safe-i18ntody-agent/codymaster | Skill | 56 | 2mo ago | none | A | 68 | Claude Code |