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 rookie-ricardo/erduo-skills --skill anthropic-style-diagramgit clone --depth 1 https://github.com/rookie-ricardo/erduo-skillsWrote 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/rookie-ricardo/erduo-skills/anthropic-style-diagram)<a href="https://agentmods.dev/skills/rookie-ricardo/erduo-skills/anthropic-style-diagram"><img src="https://agentmods.dev/badge/skills/rookie-ricardo/erduo-skills/anthropic-style-diagram/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/rookie-ricardo/erduo-skills/anthropic-style-diagram"><img src="https://agentmods.dev/badge/skills/rookie-ricardo/erduo-skills/anthropic-style-diagram.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 | $0.00172 | $0.03091 |
| Opus 5 | $0.00086 | $0.01545 |
| Sonnet 5 | $0.00034 | $0.00618 |
| Haiku 4.5 | $0.00017 | $0.00309 |
Grade A, and why
anthropic-style-diagram 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 12d 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anthropic Style Diagram
Author a semantic SVG, let the browser do the rest. scripts/render.mjs supplies the
design system, resolves the theme, audits the layout, crops the viewBox to the real ink
bounds, bakes every computed style into literal attributes, and writes the PNG.
You draw geometry and meaning. The script owns colour, theme, viewBox and export.
Never hardcode a hex value, never write a <style> block, never compute the final
viewBox height by hand.
Workflow
- Plan before drawing. Count the nodes and group them by kind — one colour ramp per kind, never one per row. Decide the diagram type (see below). If the user named 6+ components, split into an overview plus one diagram per sub-flow rather than cramming one canvas.
- Write the SVG to a working path (scratchpad or
/tmp), not the delivery path. Follow the authoring contract below;references/example-structural.svgandreferences/example-cycle.svgare the canonical shapes to imitate. - Render:
node scripts/render.mjs <working.svg> -o <target.png>. - Clear the audit. Layout warnings print on stdout. Fix every one and re-render until the run is clean. A clean run only means nothing collides — that is the floor, not the bar.
- Review the render yourself against the checklist below. Any failure sends you back to step 2. This step is not optional: the audit measures geometry, and almost everything that makes a diagram wrong lives outside geometry.
- Report the saved path, and say what the review turned up.
The review checklist
Read the rendered image, not your source. The source is what you meant; the image is what the reader gets, and only one of those can be wrong.
- Read it cold. Set aside what you set out to draw and say what the picture actually claims. If that differs from the request, the diagram is wrong — not the reader.
- Trace every arrow. Each must start and end on the shape it means, and its direction must assert something true. An arrow down the page claims the lower node is used by the upper one; say that claim out loud and check it. Placing a component below another is an assertion, not a layout convenience.
- Find the loop. If the subject has feedback — an agent, a control system, a retry path, a training cycle — locate the return edge in the image. If you cannot see it, it is not there, and a one-way drawing of a loop is simply false.
- Read every label. Accurate, ≤5 words, sentence case, unclipped, and not claiming more than the system does.
- Check the colour. Same colour must mean same category. If two nodes share a ramp only because they were next in the list, re-assign.
- Scan the whitespace. Crowded regions and dead regions are both defects, and a uniform grid of same-sized boxes means the layout is carrying no information.
What ships with it
7 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.
- 12d ago First seen · 211 lines · 172 tokens per session scan A f532ce6a2b6b
anthropic-style-diagram is a skill published in the GitHub repository rookie-ricardo/erduo-skills (935 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 3,091 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
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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.