Borrowing it
Nothing to install: this file belongs to egregore-labs/egregore. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/egregore-labs/egregore/main/.claude/skills/visual-explain/SKILL.mdgit clone --depth 1 https://github.com/egregore-labs/egregoreWrote 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/egregore-labs/egregore/visual-explain)<a href="https://agentmods.dev/skills/egregore-labs/egregore/visual-explain"><img src="https://agentmods.dev/badge/skills/egregore-labs/egregore/visual-explain.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01145 |
| Opus 5 | $0.00017 | $0.00573 |
| Sonnet 5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
visual-explain 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 7d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Explain
Explain concepts visually using ASCII diagrams, tables, flow charts, and structural maps. The visual IS the explanation — prose is secondary.
When to invoke
Trigger phrases: "explain visually", "show me a diagram", "draw this out", "chart this", "map this", "visualize this", "show me how this works", "diagram this", "sketch this out".
Also invoke when /visual-explain is used directly.
Visual vocabulary
Use the right format for the right job:
| Concept type | Visual format |
|---|---|
| Flows and pipelines | ASCII arrow diagrams (→, ↓, ──▶) |
| Architecture / components | Box diagrams with labeled connections |
| Comparisons and trade-offs | Tables with columns per option |
| Hierarchies and containment | Tree structures or nested box diagrams |
| Temporal sequences | ASCII sequence diagrams (actor columns + arrows) |
| State changes | Before/after side-by-side diagrams |
| Decision logic | Flowcharts with diamond decision nodes |
Rules
-
Lead with the visual. Always produce the diagram or table FIRST. Prose comes after, if needed at all.
-
Minimal prose. Keep explanatory text to 1-2 sentences per diagram. The visual carries the explanation — prose only clarifies what the visual cannot.
-
Prefer multiple small diagrams over one complex one. Break a system into 2-3 focused visuals rather than cramming everything into a single diagram. Each diagram should have one clear point.
-
Consistent visual language:
[ boxes ]for components, modules, services──▶or→for data flow and control flow───for connections and relationships< diamonds >for decisions( rounded )for inputs/outputs│and─for structure lines
-
System explanations follow this order:
- Structure first (what are the parts, how do they relate)
- Data flow second (what moves between them)
- State changes third (how things evolve over time)
-
Comparisons follow this order:
- Table first (options as columns, criteria as rows)
- Annotate the recommended choice with a brief reason below the table
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.
- 7d ago First seen · 133 lines · 34 tokens per session scan A 6232e8ad3f71
visual-explain is a skill published in the GitHub repository egregore-labs/egregore (282 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 1,145 once invoked, about $0.0002 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
printing-press-retro
Use when the user asks to retro, run a retrospective, file findings, or improve the Printing Press after a printed-CLI run. Trigger phrases: "retro", "retrospective", "what went wrong", "improve the press", "post-mortem", "lessons learned", "what can we improve", "file a retro", "submit findings". Do not use for…
pronounce-word
A pronunciation helper for English words, product names, project names, acronyms, and programming terms. It uses the say-it command-line tool to play the word aloud and provide pronunciation details.
教程类H5-小红书小工具
A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.
code-tour
Maintain docs/code-tour.md — the annotated guided reading of Aigon's core logic. Use when you have changed code the tour quotes, added a subsystem a new reader would need, or the user says "update the code tour", "the tour is stale", "add X to the code tour", or asks to review/refresh the code examples doc.
sansheng-distill
A book and text summarizer that creates one self-contained HTML page with five sections: an overview, chapter notes, the book’s central idea, an action checklist, and questions for judging its reliability. The page includes an embedded Mermaid mind map and works offline without a web server.
pentest-ctf
CTF (Capture the Flag) challenge solving advisory — HackTheBox, TryHackMe, PicoCTF, web/pwn/rev/crypto/forensics. Triggers on CTF, HackTheBox, HTB, TryHackMe, THM, PicoCTF, OverTheWire, pwn, reverse engineering, crypto challenge, forensics challenge, stego.