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/nourmtir0722/paperlab/agents-mdgit clone --depth 1 https://github.com/NourMtir0722/PaperlabWrote 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/nourmtir0722/paperlab/agents-md)<a href="https://agentmods.dev/instructions/nourmtir0722/paperlab/agents-md"><img src="https://agentmods.dev/badge/instructions/nourmtir0722/paperlab/agents-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 | $0.13242 | $0.13242 |
| Opus 5 | $0.06621 | $0.06621 |
| Sonnet 5 | $0.02648 | $0.02648 |
| Haiku 4.5 | $0.01324 | $0.01324 |
Grade A, and why
Paperlab AGENTS.md scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Paperlab renders physical, realistic paper as a React component. Content is a texture on a mesh that genuinely bends — text and imagery curl with perfect continuity. This file is the dense reference for agents integratin How it starts
The opening of the file, as written. The whole thing — 816 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paperlab — for coding agents
Paperlab renders physical, realistic paper as a React component. Content is a texture on a mesh that genuinely bends — text and imagery curl with perfect continuity. This file is the dense reference for agents integrating Paperlab into a project or contributing to this repo.
Reading as a human rather than as an agent? The reference is the same catalogue with everything rendering live.
Integrating Paperlab into a project
npm i paperlab three @react-three/fiber gsap
Peer requirements: React ≥ 19, three ≥ 0.160. TypeScript types ship with the package.
import { Paper } from 'paperlab'
// Simplest: a built-in preset. <Paper> owns its own <Canvas> and fills its
// parent — THE PARENT MUST HAVE A HEIGHT or the canvas renders 0px tall.
<Paper preset="receipt-unroll" />
// Or configure inline (all fields optional, validated by zod):
<Paper
sheet={{ width: 1, height: 2.6, thickness: 0.3 }}
stock="thermal" // printer | thermal | kraft | newsprint | vellum | photo-gloss | sticker
content={{ type: 'receipt', store: 'acme.dev', items: [{ name: 'Widget', price: 9.99 }] }}
behavior={{ type: 'unroll', progress: 0.6, tightness: 0.5, sway: 0.3 }}
surface={{ grain: 0.3, deckle: { edges: ['bottom'], roughness: 0.5 } }}
physics="none" // 'none' | float | tumble | dangle | taped | breeze | 'cloth' | 'strip' | {type:…}
interactive // drag handles / grab cloth
autoplay // play the behavior loop on mount
/>
Inside an existing React Three Fiber scene use <PaperMesh /> (same props, no Canvas). For galleries use <PaperField />:
import { PaperField } from 'paperlab'
<PaperField
images={['/a.jpg', '/b.jpg', '/c.jpg']}
preset="photo-print"
layout="ring" // ring | fan | spread | pile | wall | spill | sweep | book | accordion | rack | colonnade | sheet
layoutOptions={{ radius: 3, tiltDeg: 8 }}
motion={{ driver: 'autoplay', speed: 0.5 }} // autoplay | drag | none
entrance={{ type: 'rise', stagger: 0.06 }} // rise | scatter | none
/>
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.
- yesterday Changed · +346 lines · +6,026 tokens per session 8e66d999510f
- 5d ago First seen · 470 lines · 7,216 tokens per session scan A 11aadc208d1f
Paperlab AGENTS.md is an instructions file published in the GitHub repository NourMtir0722/Paperlab (51 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13,242 tokens to every session, about $0.0662 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
hyperframes CLAUDE.md
Claude Code instructions for heygen-com/hyperframes, covering hyperframes, skills, creation workflows, domain skills (loaded on demand) and skill catalog maintenance.
hyperframes AGENTS.md
AGENTS.md instructions for heygen-com/hyperframes, covering hyperframes, skills, build & test, linting & formatting and composition validation.
glyphloop CLAUDE.md
Claude Code instructions for ideoshi/glyphloop, covering glyphloop, commands, generating animations as an agent, architecture and conventions.
gsap-cookbook CLAUDE.md
Claude Code instructions for iotron/gsap-cookbook, covering agent skills — claude.md, project overview, architecture, skill flow and progressive disclosure (3-tier).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).