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 agavra/yuzudraw --skill drawgit clone --depth 1 https://github.com/agavra/yuzudrawWrote 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/agavra/yuzudraw/draw)<a href="https://agentmods.dev/skills/agavra/yuzudraw/draw"><img src="https://agentmods.dev/badge/skills/agavra/yuzudraw/draw.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 | $0.00030 | $0.02759 |
| Opus 5 | $0.00015 | $0.01380 |
| Sonnet 5 | $0.00006 | $0.00552 |
| Haiku 4.5 | $0.00003 | $0.00276 |
Grade C, and why
draw scanned grade C with 2 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 8d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
If a `yuzudraw-cli` command fails with "command not found", ask the user to install it with `curl -fsSL https://www.yuzudraw.com/install.sh | sh`, then retry. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If a `yuzudraw-cli` command fails with "command not found", ask the user to install it with `curl -fsSL https://www.yuzudraw.com/install.sh | sh`, then retry. How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/draw — Create Diagrams in YuzuDraw
Use this as the single entrypoint for diagram work. Select one family, open the matching reference, then write DSL.
Workflow
- Classify the request into one primary diagram family.
- Open the matching reference file under
references/. - Follow that reference's defaults instead of improvising a generic style.
- Pass DSL to CLI commands using a heredoc with
--dsl-stdin(see CLI Invocation Rules below). Every command MUST start withyuzudraw-cli— never use pipes,cat, orecho. - Always display the rendered ASCII output in a fenced code block in your response so the user can see it directly without expanding tool results.
- After rendering, ask the user if they'd like to save the diagram (via
create-diagramorupdate-diagram). Always prompt — don't assume they only wanted a preview.
If a yuzudraw-cli command fails with "command not found", ask the user to install it with curl -fsSL https://www.yuzudraw.com/install.sh | sh, then retry.
CLI Invocation Rules
Every CLI call MUST start with yuzudraw-cli so it can be allowlisted. Pass DSL inline via heredoc — no temp files, no pipes, no cat/echo.
- Render:
yuzudraw-cli render-ascii --dsl-stdin <<'EOF' rect "hello" id box at 5,5 size 10x3 EOF - Create:
yuzudraw-cli create-diagram --name <name> --dsl-stdin <<'EOF' ...DSL... EOF - Update:
yuzudraw-cli update-diagram --name <name> --dsl-stdin <<'EOF' ...DSL... EOF
Do NOT use pipes (cat file | yuzudraw-cli), --dsl-file, or any command that does not start with yuzudraw-cli.
Family Selection
Open architecture.md when the request is about:
- system topology
- regions, zones, groups, tiers
- cross-boundary relationships
- repeated nodes and framed areas
- high-level runtime structure
Open components.md when the request is about:
- modules, packages, services, subsystems
- interfaces, APIs, dependencies
- internal product structure
- ownership or containment boundaries
What ships with it
6 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.
- 8d ago First seen · 300 lines · 30 tokens per session scan C fe4a18b3edc2
draw is a skill published in the GitHub repository agavra/yuzudraw (50 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 2,759 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.