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 vudinh155/excali-diagram --skill diagramgit clone --depth 1 https://github.com/vudinh155/excali-diagramWrote 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/vudinh155/excali-diagram/diagram)<a href="https://agentmods.dev/skills/vudinh155/excali-diagram/diagram"><img src="https://agentmods.dev/badge/skills/vudinh155/excali-diagram/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/vudinh155/excali-diagram/diagram"><img src="https://agentmods.dev/badge/skills/vudinh155/excali-diagram/diagram.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00153 | $0.02085 |
| Opus 5 | $0.00077 | $0.01043 |
| Sonnet 5 | $0.00031 | $0.00417 |
| Haiku 4.5 | $0.00015 | $0.00209 |
Grade A, and why
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Builder (Excalidraw)
Create .excalidraw JSON files that argue visually, not merely display information.
Core philosophy: A diagram must ARGUE, not DISPLAY. The shape itself MUST BE the meaning.
- Isomorphism Test: Erase all the text — does the structure alone convey the concept? If not, redesign.
- Education Test: Does the viewer learn something concrete, or do they just see labels glued onto boxes?
Read the full methodology in
references/methodology.mdbefore designing.
Brand customization: All colors and styling live in references/color-palette.md — the single source of truth for every color choice. Read it before creating any diagram. If the user supplies a customer brand guide (e.g. input/brand-style-guide/<brand>-DESIGN.md), apply its colors via the Brand override section of that file — map the brand's colors onto the existing semantic slots (never rewrite the structure), derive any slots the brand doesn't define, and ignore brand fonts/shadows (no Excalidraw equivalent).
The 7-step workflow (REQUIRED, in order)
| Step | Task | Reference |
|---|---|---|
| S0 — Assess depth | Is this a Simple/Conceptual diagram (abstract shapes, mental models) or a Comprehensive/Technical one (concrete examples, code, real data)? If technical → research the real spec/format/names first. | methodology.md |
| S1 — Understand deeply | What does each concept DO (not what it IS)? What are the relationships, the flow, the core transformation? What must the viewer SEE? | methodology.md |
| S1.5 — Brand styling (optional) | If a customer brand guide is supplied → apply its colors via the Brand override section; pick roughness/fillStyle to match the brand's personality. Otherwise use the default palette. |
color-palette.md |
| S2 — Pick a playbook | Based on the diagram type, pick one playbook below as the primary recipe. Combine two if the diagram is hybrid. | "Pick a playbook" table |
| S3 — Map to patterns | Each major concept uses a different visual pattern (fan-out, convergence, tree, cycle…). Never a uniform card grid. | visual-patterns.md |
| S4 — Sketch the flow | Picture how the viewer's eye moves through the diagram. There must be a clear visual story. | methodology.md |
| S5 — Build JSON region by region | Build one region at a time (never the whole file at once). Use the schema + templates. Every arrow MUST be bound both ways (arrow→box AND box→arrow) — get this right as you write each arrow. | json-schema.md · element-templates.md · binding.md · rendering.md |
| S6 — Render & verify | MANDATORY: render to PNG → Read the PNG → fix → loop until it's right. Never ship a diagram from JSON alone. | rendering.md · quality-checklist.md |
What ships with it
25 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.
- .gitignore 58 B
- examples/architecture-pipeline.excalidraw 23 KB
- examples/architecture-pipeline.png 1795 KB
- examples/flowchart-approval.excalidraw 16 KB
- examples/flowchart-approval.png 1059 KB
- examples/mindmap-hierarchy.excalidraw 19 KB
- examples/mindmap-hierarchy.png 467 KB
- examples/timeline-protocol.excalidraw 14 KB
- examples/timeline-protocol.png 253 KB
- playbooks/architecture.md 4.9 KB
- playbooks/flowchart.md 4.8 KB
- playbooks/hierarchy.md 5.2 KB
- playbooks/sequence-timeline.md 4.7 KB
- references/binding.md 9.7 KB
- references/check_bindings.py 5.5 KB runs code
- references/color-palette.md 7.4 KB
- references/element-templates.md 9.9 KB
- references/json-schema.md 3.1 KB
- references/methodology.md 7.9 KB
- references/pyproject.toml 127 B
- references/quality-checklist.md 2.8 KB
- references/render_excalidraw.py 6.4 KB runs code
- references/render_template.html 1.6 KB
- references/rendering.md 6.8 KB
- references/visual-patterns.md 4.0 KB
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 · 86 lines · 153 tokens per session scan A 03edfa534ddd
diagram is a skill published in the GitHub repository vudinh155/excali-diagram (24 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 153 tokens to every session and 2,085 once invoked, about $0.0008 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.