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/glebis/humane-agentic-design/type-specimennpx skills add glebis/humane-agentic-design --skill type-specimengit clone --depth 1 https://github.com/glebis/humane-agentic-designWrote 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/glebis/humane-agentic-design/type-specimen)<a href="https://agentmods.dev/skills/glebis/humane-agentic-design/type-specimen"><img src="https://agentmods.dev/badge/skills/glebis/humane-agentic-design/type-specimen.svg" alt="Measured on agentmods" 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 | $0.00185 | $0.02098 |
| Opus 5 | $0.00093 | $0.01049 |
| Sonnet 5 | $0.00037 | $0.00420 |
| Haiku 4.5 | $0.00018 | $0.00210 |
Grade A, and why
type-specimen 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 6d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
type-specimen
Announce at start: "I'm using the humane:type-specimen skill to pick a typeface against the product's own copy."
Choosing a typeface from a foundry's own specimen tells you the font can be made to look good. It does not tell you whether your numbers align in your table at your size. This skill builds a single self-contained HTML page that sets every shortlisted family in the copy the product actually ships — the same headline, the same price column, the same empty-state sentence — so the comparison is between candidates doing the real job.
The page is standalone: one HTML file, no build step, no dependencies. Families load from the Google Fonts CSS API at view time.
Where output goes
The built specimen page and its specimen.json go in .design/specimen-<name> — the setup setting, defaulting to corpus_root. Pass -o to put them elsewhere; never let them default to the current working directory, which writes into whatever tree the agent happens to be standing in. setup/references/paths.md owns the full table.
Quick reference
| You want to | Run |
|---|---|
| Start a specimen | scripts/specimen init -o spec.json --locale ru --context "..." |
| Feed it the brief | scripts/specimen texts spec.json --from-file README.md |
| See what still needs writing | scripts/specimen texts spec.json |
| Write a slot | scripts/specimen texts spec.json --set headline="..." |
| Validate without building | scripts/specimen check spec.json |
| Build and open it | scripts/specimen build spec.json |
Config field reference: references/config.md.
The flow
1. Take the brief
Ask what the type is for, in one or two sentences: the product, the surface
(dashboard, receipt, marketing page), the reading distance, and the scripts it
must cover. Store it — --context for a sentence, --from-file for a README,
a spec, or a page of real product copy.
The brief is stored in the config and never shipped to the built page. It is for whoever writes the copy, and a specimen often gets shared before the product is announced.
What ships with it
14 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.
- conftest.py 163 B runs code
- references/config.md 3.5 KB
- scripts/specimen 297 B
- scripts/tspec/__init__.py 271 B runs code
- scripts/tspec/build.py 1.9 KB runs code
- scripts/tspec/cli.py 7.3 KB runs code
- scripts/tspec/config.py 10 KB runs code
- scripts/tspec/serve.py 1.5 KB runs code
- templates/specimen.html 48 KB
- tests/__init__.py 0 B runs code
- tests/helpers.py 495 B runs code
- tests/test_build.py 3.2 KB runs code
- tests/test_cli.py 3.8 KB runs code
- tests/test_config.py 5.9 KB runs code
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.
- 6d ago First seen · 170 lines · 185 tokens per session scan A cd1283a20d49
type-specimen is a skill published in the GitHub repository glebis/humane-agentic-design (27 stars, last pushed 4d ago), licensed MIT. It adds 185 tokens to every session and 2,098 once invoked, about $0.0009 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
figma-extract-design-system
Extract a design system from vibe-coded production apps that never had one: inventory components, mine de-facto styling into DTCG tokens, scaffold a Storybook package, port components, and optionally round-trip tokens/components into Figma. Use when the user wants to 'extract a design system', 'create a design system…
figma-version-history
List a Figma file's version history, snapshot the file at any past version, and diff two versions (added/removed/renamed pages plus deep per-component changes). Use when the user wants to inspect Figma history — triggers: 'list Figma versions', 'what versions does this file have', 'show version history', 'snapshot…
figma-blame-node
Find which Figma version introduced a specific change — a component property or a child node — via a binary search over version history (log2(N) API calls instead of N). Answers 'who added this and when'. Use when the user wants git-blame-style attribution for a Figma design — triggers: 'when was this component…
figma-comments
Read, post, reply to, and delete comments on a Figma file via the REST API — including pinning a comment to a specific node and threading replies. Use when the user wants to work with Figma comments programmatically — triggers: 'get Figma comments', 'read comments on this file', 'post a comment in Figma', 'leave a…
figma-export-tokens
Export Figma variables to design token files in DTCG, CSS custom properties, Tailwind v4/v3, SCSS, TypeScript, JSON, Style Dictionary, or Tokens Studio. Use when the user wants to pull design tokens OUT of Figma into code — triggers: 'export tokens', 'export Figma variables', 'generate CSS variables from Figma', 'turn…
figma-generate-changelog
Generate a human-readable markdown changelog between two Figma file versions — pages added/removed/renamed plus per-component changes, enriched with author handles and timestamps, ready to paste into release notes, PRs, or Storybook MDX. Use when the user wants prose history — triggers: 'generate a Figma changelog'…