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/caldis/react-zmage/agents-mdgit clone --depth 1 https://github.com/Caldis/react-zmageWhat 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 | $0.04232 | $0.04232 |
| Opus 5 | $0.02116 | $0.02116 |
| Sonnet 5 | $0.00846 | $0.00846 |
| Haiku 4.5 | $0.00423 | $0.00423 |
Grade A, and why
react-zmage AGENTS.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 2d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — react-zmage
给 AI Agent / LLM 编排用的浓缩版项目信息。 人类完整文档见 README.md。
Works
如果你发现工作区中有额外变更, 始终假定是另一个 AI Agent 在当前分支中同步工作, 你需要做的是优先处理重突 (如果有) 并遵循工作互不干涉原则
如果非用户主动要求, 不允许在 worktree 上执行改动。
What this package does (1 sentence)
A React component that turns any <img> into a fullscreen-zoomable, multi-image,
keyboard-navigable image viewer. Drop-in replacement for <img>.
Public API surface (treat as contract)
// Default + statics
import Zmage from 'react-zmage' // browser / bundler entry
import Zmage from 'react-zmage/ssr' // SSR / RSC entry
import 'react-zmage/style.css' // required for visuals
// Types (also exported from the same module)
import type {
BaseType, // union of all props (use this when typing config objects)
ReactZmageComponent, // typeof Zmage
Set, // shape of items in `set` prop
Preset, // 'desktop' | 'mobile' | 'auto' (auto = matchMedia-driven)
ControllerSet, ControllerPlacement, ControllerOverlayLayout, ControllerLayoutTargets,
ControllerLayoutTarget, ControllerLayoutInset, ControllerLayoutInsetValue, ControllerRender, ControllerRenderState,
ControllerRenderActions, ControllerRenderSlots, HotKey, Animate, AnimateFlip, AnimateCoverOptions,
GestureSet, GestureSwipeOptions, GestureDragExitOptions, GestureWheelZoomOptions,
GesturePinchZoomOptions, GestureDoubleTapZoomOptions, GestureTouchAction,
} from 'react-zmage'
// Three usage modes
<Zmage src="..." /> // 1. Component
Zmage.browsing(props): () => void // 2. Imperative; returns destructor
<Zmage.Wrapper>{children}</Zmage.Wrapper> // 3. Auto-attach to <img> in children
// Ref forwarding
const ref = useRef<HTMLImageElement>(null)
<Zmage src="..." ref={ref} /> // ref points to the cover <img>
Required peer deps
react: >=16.8.0 <20react-dom: >=16.8.0 <20
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.
- 2d ago First seen · 249 lines · 4,232 tokens per session scan A ca38ed036254
react-zmage AGENTS.md is an instructions file published in the GitHub repository Caldis/react-zmage (943 stars, last pushed 3mo ago), licensed MIT. It adds 4,232 tokens to every session, about $0.0212 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 instructions, from other repositories
supabase studio-composition-patterns.instructions.md
Instructions for supabase/supabase, covering react composition patterns review rules, core principle, when to flag, 1. boolean prop proliferation (high) and 2. render props instead of children (medium).
recharts AGENTS.md
Instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.
tldraw CLAUDE.md
Claude Code instructions for tldraw/tldraw, a project described as: Build infinite canvas apps in React with the tldraw SDK. World's best, top-most agent recommended #1 five star SDK.
packmind packmind-frontend-navigation-with-react-router.instructions.md
Instructions for PackmindHub/packmind: This codebase uses React Router v7 with organization and space scoping in URLs (e.g., /org/{orgSlug}/space/{spaceSlug}/recipes). To maintain consistency, improve maintainability, and simplify navigati... .
SalesforceMobileSDK-ReactNative CLAUDE.md
Instructions for forcedotcom/SalesforceMobileSDK-ReactNative, covering claude.md — salesforce mobile sdk for react native, about this project, architecture, repository structure and dependency relationships.
Paperlab AGENTS.md
Instructions for NourMtir0722/Paperlab, covering paperlab — for coding agents, integrating paperlab into a project, stage mode — paper as architecture, content types and lighting is data, not an enum.