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 agentmods add skills/danium/practicaltypography/typographynpx skills add danium/practicaltypography --skill typographygit clone --depth 1 https://github.com/danium/practicaltypographyWhat 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 | $0.00065 | $0.01450 |
| Opus 5 | $0.00032 | $0.00725 |
| Sonnet 5 | $0.00013 | $0.00290 |
| Haiku 4.5 | $0.00006 | $0.00145 |
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 yesterday.
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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typography
Good typography reinforces the meaning of the text and conserves the reader's attention. Start with body text, but never apply body-text rules to every role. Treat Practical Typography as a benchmark, not a compliance standard. Rule IDs point to provenance.md, which distinguishes source guidance (PT), project choices (DEVIATION), and current external requirements (CURRENT).
Load only what the task needs [ROUTE-001]
- Character substitutions, punctuation, whitespace, emphasis, or literal text: composition.md
- Paragraphs, headings, lists, quotations, tables, styles, pagination, columns, or grids: layout.md
- Font selection, pairing, glyphs, features, or licensing: fonts.md
- Websites, responsive measure, actual font use, fallbacks, or accessibility: web.md
- Print, slides, email, resumes, tables of numbers, or PDF delivery: media.md
- Non-English, non-Latin, bidirectional, or mixed-script text: international.md
- Authority, scope, freshness, and evaluation coverage for a rule: provenance.md
Do not load every reference by default. A PDF containing Arabic code examples, for example, needs media.md, international.md, and the literal-text section of composition.md; a simple English print paragraph does not need web.md.
Precedence
Apply this order whenever recommendations conflict [CORE-002]:
- content correctness and semantics;
- accessibility, language conventions, and legal or license constraints;
- user intent and delivery medium;
- Practical Typography benchmarks;
- project presets and optional taste.
Preserve the user's requested aesthetic as far as higher-priority constraints allow. If it departs from a benchmark, label the departure once and give the benchmark alternative without repeatedly arguing the point.
Gated audit
1. Classify context [AUDIT-001]
Identify the medium and delivery format, reading environment, intended audience, language and script, user intent, and the roles present: running prose, display heading, navigation, caption, table, code, data, and so on. State a material assumption if it cannot be verified.
What ships with it
7 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.
- yesterday First seen · 95 lines · 65 tokens per session scan A 51decacab8d7
typography is a skill published in the GitHub repository danium/practicaltypography (27 stars, last pushed 5d ago), licensed MIT. It adds 65 tokens to every session and 1,450 once invoked, about $0.0003 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.
Other skills, from other repositories
cross-browser-typography-qa
Use this skill when web text looks clipped, flattened, wrapped incorrectly, misaligned, or materially different between Chromium and WebKit/Safari. Treat text rendering as both a geometry problem and a visual paint problem: passing DOM bounds does not prove that every glyph is intact.
fonts
Personal font reference and setup helper. Use when discussing typography, choosing fonts for a project, setting up font imports, or when the user is starting a new project and needs to pick typefaces.
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…