What is claude-skill-typst CLAUDE.md?

A development guide for a Typst skill. Typst is a markup-based system for creating formatted documents, and the guide explains how its agent-facing content is organised and routed.

Use it when adding Typst guidance, examples, searches, compatibility notes, or validation rules to the skill.

It keeps the skill's documentation and compatibility guidance in the expected places, including support for different Typst versions.

How lucifer1004/claude-skill-typst configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lucifer1004/claude-skill-typst. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/lucifer1004/claude-skill-typst/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lucifer1004/claude-skill-typst

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lucifer1004/claude-skill-typst/claude-md/github.svg)](https://agentmods.dev/instructions/lucifer1004/claude-skill-typst/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lucifer1004/claude-skill-typst/claude-md"><img src="https://agentmods.dev/badge/instructions/lucifer1004/claude-skill-typst/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lucifer1004/claude-skill-typst/claude-md"><img src="https://agentmods.dev/badge/instructions/lucifer1004/claude-skill-typst/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,522 This file is loaded in full into every session.

When invoked 1,522 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01522	$0.01522
Opus 5	$0.00761	$0.00761
Sonnet 5	$0.00304	$0.00304
Haiku 4.5	$0.00152	$0.00152

Measured 4d ago against content hash 246d016d76d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-skill-typst CLAUDE.md 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 4d 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.

CLAUDE.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Guide

What This Is

A skill that teaches AI agents how to work with Typst. Everything agent-facing lives under skills/typst/. The root README.md is for humans browsing GitHub, and skills/typst/ should not contain a separate human-facing README.md.

The current bundled skill targets Typst 0.15+. Typst 0.14.2 support was dropped; the typst-0.14.2 repository tag freezes the last compatible snapshot.

The stable API index (data/api.json) auto-follows the latest Typst release via .github/workflows/update-api.yml. Two exporter variants live in tools/: typst-api-exporter.rs tracks upstream main, while typst-api-exporter-stable.rs must compile against the latest release tag — update it when a new minor release changes the upstream API.

Project Structure

repo root (NOT bundled)               skills/typst/ (bundled skill)
├── tools/          # Data generation  ├── SKILL.md       # Entry point
├── tests/          # Test suite       ├── *.md           # Reference docs
├── evals/          # Harbor eval tasks (local only, see evals/README.md)
├── .github/        # CI workflows     ├── agents/        # Agent definitions
├── Justfile        # Task runner      ├── scripts/       # Search & validation
├── pixi.toml       # Dependencies    ├── data/          # JSON indexes
├── CLAUDE.md       # Dev guide        └── examples/      # Runnable .typ files
└── README.md       # Human readme

Architecture: The Routing Rule

SKILL.md is the single entry point. It contains:

Detection patterns and quick reference
Two routing tables — Writing Documents (user-facing) and Developing Packages and Templates (developer-facing) — that direct agents to the right *.md file by task
Package search, common errors, and examples

Every new .md file or capability MUST be registered in SKILL.md's routing table. If it's not in the table, agents won't find it. Dead content is worse than no content. This is enforced by tests/test_structure.py.

Read the full file on GitHub · 136 lines

Changes

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.

4d ago Changed · +8 lines · +132 tokens per session 246d016d76d8
9d ago First seen · 128 lines · 1,390 tokens per session scan A 7285b008ec3d

Subscribe to this mod's changes

claude-skill-typst CLAUDE.md is an instructions file published in the GitHub repository lucifer1004/claude-skill-typst (123 stars, last pushed yesterday), licensed MIT. It adds 1,522 tokens to every session, about $0.0076 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 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

claude-skill-typst: Instructions file for Claude Code