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 OutlineDriven/odin-claude-plugin --skill typography-auditgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/typography-audit)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/typography-audit"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/typography-audit/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/outlinedriven/odin-claude-plugin/typography-audit"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/typography-audit.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 | $0.00045 | $0.04478 |
| Opus 5.5 | $0.00018 | $0.01791 |
| Sonnet 5.5 | $0.00009 | $0.00896 |
| Haiku 4.5 | $0.00005 | $0.00448 |
Grade A, and why
typography-audit 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 1mo 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typography audit
Contract
| Field | Bound contract |
|---|---|
| Trigger | User says audit my typography, fix the fonts, review my type, font pairing, type scale, or web typography |
| Authority | Human-gated: applies fixes only when the user explicitly requests them; otherwise read-only with no file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | Chat output: file:line findings with concrete CSS/HTML fix suggestions, plus not-verifiable-from-source verdicts for rules that need rendered metrics |
| Done | Report covers all 10 categories; every finding is either a verified file:line violation with a concrete fix or a not-verifiable-from-source verdict naming the rendered metric that would decide it; findings are ordered by impact with no fabricated file:line violations |
Inputs
- Project directory or file set to audit (required). Accept a path, glob, or the current working directory.
- Optional: brand guidelines, style guide, or design tokens file if available.
- Optional: specific category filter (e.g., only spacing, only font) to narrow scope.
Procedure
- Collect all CSS, SCSS, Less, HTML, JSX, TSX, Vue, and Svelte files in scope. Skip node_modules, dist, build, vendor, and .git directories. Done when: every in-scope source file is collected or reported unreadable.
- For each file, extract font-family declarations, font-size values, line-height values, letter-spacing values, color declarations on text elements, @font-face blocks, font-feature-settings, and typographic HTML elements (h1-h6, p, blockquote, ul, ol, li, em, strong, small, sup, sub, abbr, cite, q, dl, dt, dd). Done when: every collected file has its typographic surface extracted.
- Audit against the following 10-category rule set. For each violation found, record the file path, line number, rule name, severity (critical/high/medium/low), and a concrete CSS or HTML fix. When a rule's verdict depends on rendered metrics that static source cannot decide, record the finding as not-verifiable-from-source: name the rule, the files and declarations examined, and the rendered metric that would decide it. Rules that commonly need rendered facts include size-line-length (measure depends on font metrics and container width), layout-widows-orphans and layout-optical-balance (line breaking), pairing-contrast-harmony and pairing-stress-skeleton (x-height and stress need glyph or font-metric inspection), brand-dark-backgrounds (contrast when colors resolve through custom properties the scan cannot statically resolve), display-grid-breaking (baseline rhythm is rendered), and display-drop-caps (rendered cap metrics). Never force a file:line verdict for a rendered-metric rule. Done when: all 10 categories have been checked, with every finding either verified at file:line or recorded as not-verifiable-from-source.
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.
- 1mo ago First seen · 162 lines · 45 tokens per session scan A 45155cf01859
typography-audit is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (39 stars, last pushed 25d ago), licensed Apache-2.0. It adds 45 tokens to every session and 4,478 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…