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/lenxism/ives/typographynpx skills add lenxism/ives --skill typographygit clone --depth 1 https://github.com/lenxism/ivesWhat 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 | $0.00117 | $0.01005 |
| Opus 5 | $0.00059 | $0.00502 |
| Sonnet 5 | $0.00023 | $0.00201 |
| Haiku 4.5 | $0.00012 | $0.00101 |
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 2d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typography
Typography is the most critical part of interface design. Sloppy, inconsistent usage of font sizes, weights, and colors is the clearest signal that a designer doesn't know what they're doing.
Read references/typography-knowledge.md for detailed examples and analysis of real-world apps.
The Rule of Four
Limit yourself to a maximum of four type sizes or less. This rule can be broken, but only when you understand why the boundaries exist.
The evidence: Instagram's home screen uses essentially one type size (15pt) with only a smaller 12pt for story labels. Twitter uses three sizes for its entire timeline. iOS Settings uses two sizes on internal pages. Facebook Messenger's main screen: three sizes.
When apps use 5-6+ sizes (like Facebook's Discover tab), they immediately look disorganized and lack cohesion.
The four roles
Most well-designed interfaces combine:
- Title — Page or section titles
- Body/Subtitle — Primary content, list items, navigation
- Action items — Buttons, links, interactive elements (often same size as body, differentiated by color/weight)
- Metadata — Timestamps, helper text, secondary info
You can often collapse these to 2-3 sizes. The fewer sizes, the cleaner the interface.
Extending Without Adding Sizes
Change meaning without adding sizes by varying:
- Color — Same size, different color: black for titles, gray for subtitles, blue for actions
- Weight — Bold for names, regular for body, medium for interactive (Instagram uses subtle weight changes for actionable profile names)
- Position — Right-aligned text reads as a value/definition of the left-aligned label (iOS Settings pattern)
- Decoration — Underlines, background colors, or pill shapes on action items
- Case — ALL CAPS at a smaller size can serve as a section divider without adding a new size
Font Weight as Hierarchy
Weight controls emphasis and interactive meaning:
- Bold/Heavy — Primary titles, emphasis
- Semibold/Medium — Interactive elements, secondary emphasis
- Regular — Body text, descriptions
- Light — Use very sparingly. Thin weights at small sizes become unreadable.
What ships with it
1 file 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.
- 2d ago First seen · 92 lines · 117 tokens per session scan A e73bada623fb
typography is a skill published in the GitHub repository lenxism/ives (5 stars, last pushed 6mo ago), licensed MIT. It adds 117 tokens to every session and 1,005 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…