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 rules/zoxknez/ai-coding-rules/94-multimodal-contextgit clone --depth 1 https://github.com/zoxknez/ai-coding-rulesWrote 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/rules/zoxknez/ai-coding-rules/94-multimodal-context)<a href="https://agentmods.dev/rules/zoxknez/ai-coding-rules/94-multimodal-context"><img src="https://agentmods.dev/badge/rules/zoxknez/ai-coding-rules/94-multimodal-context.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 | $0.00000 | $0.00288 |
| Opus 5 | $0.00000 | $0.00144 |
| Sonnet 5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
94-multimodal-context 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.
What it actually says
Multimodal Visual Feedback Rule
When working on UI-related files (Components, Pages, App Router, Styles):
- Verify Vision Capability: Check if you have vision capabilities (e.g., using Gemini 3 or GPT-4o).
- Request Baseline: Before making any styling or layout changes, request a screenshot of the current UI.
- Example: "I'm about to modify the login form. Please provide a screenshot of the current state for baseline comparison."
- Implement Changes: Proceed with implementation.
- Request Verification: After applying changes, request a new screenshot to verify layout, alignment, and "vibes."
- Example: "Changes applied. Please provide a new screenshot so I can verify the visual outcome."
- Self-Correct: If discrepancies are found between the mockup/intent and the actual screenshot, perform a self-correction pass.
Note: Visual context is 10x more effective than code analysis for detecting CSS 'jank' or alignment issues.
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 · 19 lines · 288 tokens per session scan A 94a0652d85b5
94-multimodal-context is a cursor rule published in the GitHub repository zoxknez/ai-coding-rules (28 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 288 tokens. 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 cursor rules, from other repositories
ui-components
USE WHEN: Building UI components, structuring layouts, and applying styles using Tailwind CSS.
frontend-theme-guidelines
Cursor rule "frontend-theme-guidelines" from KroMiose/nekro-agent, covering 前端主题系统开发指南, 主题系统架构, 核心文件结构, 基本原则 and 主题使用指南.
ui-design-system
UI, design tokens and mobile-first rules.
taste-enforcement
These dials drive all downstream decisions. Adjust per-prompt when the user specifies a different mood.
ui-architecture
Enforces single-page, context-centric UI patterns for the object-centric workspace.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.