Visual Explainer is an agent skill that turns complex terminal output into self-contained HTML pages with diagrams, tables, and styled explanations. It is for people who want coding agents to present architecture reviews, diffs, plans, and other structured information in a browser. The catalogue contains its skill, commands, rules, and plugin packaging.
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 agentmods add commands/nicobailon/visual-explainer/generate-web-diagramgit clone --depth 1 https://github.com/nicobailon/visual-explainerWrote 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/commands/nicobailon/visual-explainer/generate-web-diagram)<a href="https://agentmods.dev/commands/nicobailon/visual-explainer/generate-web-diagram"><img src="https://agentmods.dev/badge/commands/nicobailon/visual-explainer/generate-web-diagram.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 | $0.00016 | $0.00283 |
| Opus 5 | $0.00008 | $0.00142 |
| Sonnet 5 | $0.00003 | $0.00057 |
| Haiku 4.5 | $0.00002 | $0.00028 |
Grade A, and why
generate-web-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 5d 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.
What it actually says
Load the visual-explainer skill and generate an HTML visual explainer for: $@
If $@ contains the literal --quick flag, remove that flag from the topic, read ./quick/README.md and ./quick/schema.json, and emit a compact JSON spec instead of HTML. In Pi, call visual_explainer with action: "render_quick", a descriptive filename, and the spec. In other harnesses, save the spec and run node ./quick/render.mjs <spec.json> <output.html> from the installed skill directory. If the topic does not fit the schema, validation fails, or rendering errors, continue with the full HTML workflow below. Without --quick, do not use quick mode.
Use the skill’s reference routing and final checklist. Pick a representation that fits the topic: Mermaid for connected flows/topologies; CSS cards for text-heavy explanations; tables for matrices; timelines for linear history.
Write to ~/.agent/diagrams/ with a descriptive filename and open the result in the browser. In Pi package installs, this is an explicit visual request: use visual_explainer.prepare when planning/context scouting helps, then visual_explainer.render with the complete HTML.
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.
- 5d ago First seen · 13 lines · 16 tokens per session scan A a230ddc47948
generate-web-diagram is a command published in the GitHub repository nicobailon/visual-explainer (9,639 stars, last pushed 7d ago), licensed MIT. It adds 16 tokens to every session and 283 once invoked, about $0.0001 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 commands, from other repositories
screenshot
Capture a screenshot of a window or DOM element.
generate
Generation is browser-backed. Keep the Flovart UI open and check readiness first.
stt
Transcribe a local audio file or remote audio URL into text.
brand-generate
Generate an on-brand document from a saved Brand Profile.
list
List available Piper TTS TTS voices with optional filtering.
firecrawl
You are an expert at web scraping, crawling, and data extraction using Firecrawl's API and SDKs.