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 instructions/jakedismo/visual-explainer-extension/gemini-mdgit clone --depth 1 https://github.com/Jakedismo/visual-explainer-extensionWrote 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/instructions/jakedismo/visual-explainer-extension/gemini-md)<a href="https://agentmods.dev/instructions/jakedismo/visual-explainer-extension/gemini-md"><img src="https://agentmods.dev/badge/instructions/jakedismo/visual-explainer-extension/gemini-md.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 | $0.00806 | $0.00806 |
| Opus 5 | $0.00403 | $0.00403 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00081 | $0.00081 |
Grade A, and why
visual-explainer-extension GEMINI.md 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
visual-explainer
An agent skill that turns complex terminal output into styled HTML pages you actually want to read.
ABOUTME: This project is an agent skill for Gemini CLI that generates beautiful, self-contained HTML pages for diagrams, diff reviews, plan reviews, and data tables. It also includes native AI image generation tools.
Project Overview
visual-explainer replaces ASCII art and box-drawing tables with interactive HTML pages featuring real typography, dark/light themes, and Mermaid diagrams. It also provides built-in tools for generating images, icons, and patterns via the Gemini API.
Main Technologies
- HTML/CSS: Vanilla implementation for self-contained portability.
- Mermaid.js: For flowcharts, sequence diagrams, and topology.
- Chart.js: For dashboards and metrics.
- Node.js / MCP: Native image generation tools using the Gemini API.
Extension Structure
gemini-extension.json: Manifest defining extension metadata and MCP server.package.json: Project metadata and Node.js dependencies.commands/: Custom slash commands (TOML format) available in Gemini CLI.skills/: Agent-activatable workflows (e.g.,visual-explainer/SKILL.md).references/: Reference material the model reads before generating output.templates/: Reference HTML structures for different visualization types.
Available Commands
Visualization Commands
| Command | Description |
|---|---|
/diff-review |
Visual diff review with architecture comparison. |
/fact-check |
Verify accuracy of a document against code. |
/generate-slides |
Generate a magazine-quality slide deck. |
/generate-visual-plan |
Generate a visual implementation plan. |
/generate-web-diagram |
Generate an HTML diagram for any topic. |
/plan-review |
Compare a plan against the codebase. |
/project-recap |
Mental model snapshot for context-switching. |
/visual-code-explain |
Explain the logic of a generated code file, mapping user intent to implementation. |
/code-archetype |
Generate a technical icon and structural card for a module or subsystem. |
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.
- 4d ago First seen · 62 lines · 806 tokens per session scan A f9edfeaf0ed7
visual-explainer-extension GEMINI.md is an instructions file published in the GitHub repository Jakedismo/visual-explainer-extension (8 stars, last pushed 6mo ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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 2026-08-31.
Other instructions, from other repositories
gemini-extension GEMINI.md
Instructions for conversiontools/gemini-extension, covering conversion tools, if the tools are not available, how to convert a file, build a custom converter (ai studio) and tip: prefer the ctio cli when available.
gimp-mcp CLAUDE.md
Claude Code instructions for maorcc/gimp-mcp, covering claude.md, architecture, installation & setup, gimp plugin installation and mcp server configuration.
final-pos-mcp GEMINI.md
Gemini CLI instructions for Final-Commerce/final-pos-mcp, covering building final pos apps, the build loop, shipping and rules that will save you.
meteocontrol-mcp GEMINI.md
Gemini CLI instructions for nielsvbrecht/meteocontrol-mcp, covering meteocontrol extension context, core mandates & communication style, operational guidelines, 1. performance analysis & metrics translation and 2. proactive troubleshooting.
gemini-mem GEMINI.md
Instructions for djinn-soul/gemini-mem, covering gemini.md, memory behavior and operator notes.
victoriametrics-logs-mcp GEMINI.md
Gemini CLI instructions for nielsvbrecht/victoriametrics-logs-mcp, covering core capabilities, victoriametrics (metrics), victorialogs (logs), available tools and metrics tools.