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 glebis/humane-agentic-design --skill brand-illustrategit 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/brand-illustrate)<a href="https://agentmods.dev/skills/glebis/humane-agentic-design/brand-illustrate"><img src="https://agentmods.dev/badge/skills/glebis/humane-agentic-design/brand-illustrate/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/glebis/humane-agentic-design/brand-illustrate"><img src="https://agentmods.dev/badge/skills/glebis/humane-agentic-design/brand-illustrate.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 | $0.00141 | $0.03077 |
| Opus 5 | $0.00071 | $0.01538 |
| Sonnet 5 | $0.00028 | $0.00615 |
| Haiku 4.5 | $0.00014 | $0.00308 |
Grade A, and why
brand-illustrate 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 11d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
brand-illustrate
Announce at start: "I'm using the humane:brand-illustrate skill to generate an on-brand illustration set from existing tokens."
Ring-2 humane skill. It reads the on-brand contract a design-tokens set already
carries (palette with roles, fonts, shape, and the $extensions brand block) and
walks the user through a short questionnaire — JTBD-style, one step at a time — to
scaffold prompts that stay on-brand and generate a set that reads as one family.
Generators live outside the plugin. This skill is a thin adapter: it composes the prompt and shells out to whichever backend is installed. It never bundles a generator, an API client, or your keys.
No backend is not a dead end. The prompts are what this skill actually
produces — assembled from the palette, the brand block, and the merged de-slop
negatives — and they are the same whether or not an API call follows. With no
generator present, a run writes prompts.md with every final prompt at its
target size, plus metadata.json and the recipe. Paste them into any image tool,
or install a backend and resume with run --recipe.
Finding a backend
Discovery makes no assumption about which agent you run. First hit wins:
| # | Source | |
|---|---|---|
| 1 | The image_backend setting as <name> or <name>:/path/to/script |
project humane.json > ~/.humane/config.json > HUMANE_IMAGE_BACKEND; auto means "no explicit choice" |
| 2 | HUMANE_SKILLS_DIR=/one:/two |
extra skill roots to search |
| 3 | Known agent skill roots | ~/.claude/skills, ~/.codex/skills, ~/.config/skills, project .agents/skills and .claude/skills, and the plugin's own tree |
| 4 | PATH |
a generator packaged as a plain executable |
Row 1 is the layered setting setup owns, not the environment variable alone —
a config file legitimately outranks a variable exported in the calling shell.
scripts/illustrate.py backends -v prints what was found and every location
searched — use it before concluding anything is missing.
What ships with it
4 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.
- 11d ago First seen · 251 lines · 141 tokens per session scan A 2f70ade9352b
brand-illustrate is a skill published in the GitHub repository glebis/humane-agentic-design (28 stars, last pushed today), licensed MIT. It adds 141 tokens to every session and 3,077 once invoked, about $0.0007 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-slides
Author Figma Slides presentations — list/create/duplicate/reorder/delete slides, read the slide grid, add text and shapes to a slide, set slide background color, set or read slide transitions (dissolve, slide-from, push-from, smart-animate), focus a slide, and toggle skip. Use when the user wants to build or edit a…
hps-retro-tv
A family history told through five decades of home movies — the opening question, the eras, and what the footage reveals. Built as a decision-grade story deck for family, close friends.
ve-terminal-mono
OpenDesign from the CLI: driving the full design workflow with the od command — scripted, composable, agent-ready. Built as a decision-grade AI literacy deck for developers, power users.
html-ppt-zhangzara-blue-professional
OpenDesign's QBR for the executive committee: what moved, what stalled, and the resource reallocation ask. Built as a decision-grade corporate strategy deck for executive committee.
html-ppt-zhangzara-pink-script
A wedding-anniversary tribute photo essay — a decade in scenes, the turning points, and the quiet meaning of staying. Built as a decision-grade story deck for couple, family, friends.
html-ppt-zhangzara-raw-grid
A brutalist poster-series case study for a music festival — the concept, the system, and how it scaled across formats. Built as a decision-grade design craft deck for design peers, client.