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 clearsmog/claude-skills --skill typstgit clone --depth 1 https://github.com/clearsmog/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/clearsmog/claude-skills/typst)<a href="https://agentmods.dev/skills/clearsmog/claude-skills/typst"><img src="https://agentmods.dev/badge/skills/clearsmog/claude-skills/typst/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/clearsmog/claude-skills/typst"><img src="https://agentmods.dev/badge/skills/clearsmog/claude-skills/typst.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 | $0.00044 | $0.02745 |
| Opus 5 | $0.00022 | $0.01373 |
| Sonnet 5 | $0.00009 | $0.00549 |
| Haiku 4.5 | $0.00004 | $0.00275 |
Grade A, and why
typst 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 9d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typst Skill
Current version: Typst 0.14.2 (Dec 2025)
Smart Defaults
If you know nothing else, follow these rules:
- Always import
@local/qk:2.1.0—#import "@local/qk:2.1.0": * - Always use
qk-docorqk-reportpreset (unless user specifies custom) - Always use touying for presentations (not raw page dimensions) — see
references/touying-guide.md - Always
#set figure(placement: auto)— prevents blank half-pages - Always add
alt:to images —image("path.png", alt: "description") - Always escape
$in content — scan for bare$before compiling - Default fonts: Libertinus Serif (body), Inter (headings), New Computer Modern Math (math), Fira Code (code)
- Default compile:
typst compile --root .. Source/<file>.typ - When in doubt about template: Study Guide
- When in doubt about visual tool: diagrams → fletcher; charts → see decision tree (simple → cetz-plot, statistical → matplotlib+seaborn, grammar → plotnine, complex → matplotlib)
- Always scan project for existing
.typfiles and match their style (fonts, colors, qk preset) unless user specifies otherwise
New Document Decision Tree
User request → scan for keywords:
"resume/CV/job" → CV / Résumé template
"slides/presentation" → Presentation (touying — metropolis default)
"lecture/class/academic" → Academic Lecture (touying — university theme)
"essay/thesis/paper" → Essay
"report/brief/client" → Business Report
"research/analysis" → Research Report
"study guide/revision" → Study Guide
"reference/glossary" → Annotated Reference
"cheatsheet/reference card/formula sheet" → Cheatsheet template
"exam/problem set/homework" → Exam template
"flashcard/Q&A/quiz" → Flashcard template
ambiguous? → ask purpose + audience → pick template
Steps:
- Auto-detect template from keywords above
- Import
@local/qk:2.1.0at top - Use
qk-docorqk-reportpreset when applicable - Auto-select template. State choice in Phase 3 summary. User can re-invoke with explicit type override if wrong.
- Build from
references/templates.md - Custom styles are fine — templates are starting points, not constraints
What ships with it
13 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.
- references/common-patterns.md 3.0 KB
- references/component-library.md 6.4 KB
- references/data-driven.md 3.9 KB
- references/layout-patterns.md 6.2 KB
- references/math-pitfalls.md 2.8 KB
- references/packages.md 4.8 KB
- references/quality-gates.md 2.0 KB
- references/quick-ref.md 4.4 KB
- references/symbols.md 1.5 KB
- references/templates.md 12 KB
- references/tool-routing.md 12 KB
- references/touying-guide.md 6.5 KB
- references/visual-verification.md 2.9 KB
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.
- 9d ago First seen · 227 lines · 44 tokens per session scan A dc7bc77bac3b
typst is a skill published in the GitHub repository clearsmog/claude-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 2,745 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
replicate-runner
Use when run AI models on Replicate cloud API. Deploy image generation, video creation, audio processing, and custom models without managing infrastructure. Use when working with replicate runner.
decision-heuristics
A set of heuristics for making difficult personal decisions such as changing jobs, buying a home, moving, forming a partnership, or getting married. It is intended for major choices, not everyday decisions.
wealth-structure
A framework for thinking about wealth through ownership, responsibility, leverage, and avoiding risks that could end your progress.
acceptance
A personal decision framework for difficult situations, built around three choices: change the situation, accept it, or leave it.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.