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 viktorbezdek/skillstack --skill visual-communicationgit clone --depth 1 https://github.com/viktorbezdek/skillstackWrote 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/viktorbezdek/skillstack/visual-communication)<a href="https://agentmods.dev/skills/viktorbezdek/skillstack/visual-communication"><img src="https://agentmods.dev/badge/skills/viktorbezdek/skillstack/visual-communication/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/viktorbezdek/skillstack/visual-communication"><img src="https://agentmods.dev/badge/skills/viktorbezdek/skillstack/visual-communication.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 | $0.00125 | $0.02067 |
| Opus 5.5 | $0.00050 | $0.00827 |
| Sonnet 5.5 | $0.00025 | $0.00413 |
| Haiku 4.5 | $0.00013 | $0.00207 |
Grade A, and why
visual-communication 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 1mo 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Communication
A diagram is not decoration — it is compression. If three paragraphs describe the same flow a diagram shows in 20 seconds, the diagram wins. If a diagram takes ten minutes to read, the paragraphs won.
When a diagram beats prose
| Signal | Diagram |
|---|---|
| The reader needs to understand a process with branches | Flowchart |
| The reader needs to see who talks to whom and when | Sequence diagram |
| The reader needs to understand state transitions | State diagram |
| The reader needs to see what depends on what | Component / dependency diagram |
| The reader needs the data model | ER diagram |
| The reader needs the big picture of a system | C4 diagram |
| The reader needs a 2×2 trade-off / matrix | Quadrant / matrix |
When a diagram does NOT beat prose:
- Simple linear sequences (1 → 2 → 3) — a list is clearer.
- Content-heavy ideas — diagrams force compression that loses nuance.
- When the diagram would have 30+ nodes — split or describe.
- When the reader needs exact values — a table beats a chart.
Picking the right diagram
Flow-oriented (what happens in what order)?
├── With branches/decisions → flowchart
├── Between actors/components over time → sequence diagram
└── With explicit states → state diagram
Structure-oriented (how is it organized)?
├── Data → ER diagram
├── Code → class diagram
├── System at high level → C4 diagram
└── Components + dependencies → dependency graph
Comparison-oriented?
├── 2 dimensions, 4 quadrants → quadrant chart
└── N options, M criteria → matrix / table (often not a diagram)
Full decision tree with worked examples in references/diagram-selection-matrix.md.
Mermaid is the default
Mermaid is the best default for engineering diagrams because:
- Text-based → versionable in git.
- Renders natively in GitHub, GitLab, Notion, Obsidian, VS Code.
- Low cost to edit; no image file to re-export.
- Adequate for 90% of diagrams engineering teams draw.
Use PNG/SVG diagrams only when Mermaid cannot express the idea (complex physical diagrams, highly custom layouts).
What ships with it
5 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.
- 1mo ago First seen · 227 lines · 125 tokens per session scan A de3c69b2d0d1
visual-communication is a skill published in the GitHub repository viktorbezdek/skillstack (14 stars, last pushed 4mo ago), licensed MIT. It adds 125 tokens to every session and 2,067 once invoked, about $0.0005 per session on Opus 5.5. 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
ai-product
Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
accesslint-audit
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.