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/clientio/joint/claude-mdgit clone --depth 1 https://github.com/clientIO/jointWhat 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 | $0.01220 | $0.01220 |
| Opus 5 | $0.00610 | $0.00610 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
joint CLAUDE.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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
JointJS is a JavaScript/TypeScript diagramming library for building visual and no-code/low-code applications. It's a Yarn workspace monorepo with multiple packages.
Stack: Node 22.14.0, Yarn 4.18.0, TypeScript 5.8 (5.9 in joint-react),
Grunt (build), QUnit/Karma/Mocha/Jest (testing)
Common Commands
# Install dependencies
yarn install
# Build distribution files (runs Grunt)
yarn dist
# Run all tests (QUnit + Jest + TypeScript checks)
yarn test
# Run specific test types
yarn test-server # Server-side tests (Node.js)
yarn test-client # Client-side tests (Browser with Karma)
yarn test-ts # TypeScript type definition tests
yarn test-e2e # End-to-end tests (Puppeteer)
# Linting
yarn lint # Check all packages
yarn lint-fix # Auto-fix errors
# Build bundles
yarn build
yarn build-bundles
Running Single Tests
For joint-react Jest tests:
cd packages/joint-react
yarn jest --testPathPatterns="ComponentName"
Architecture
Monorepo Packages (/packages)
- @joint/core - Main diagramming library (MVC architecture, SVG rendering)
- @joint/react - React bindings and hooks (Rollup + esbuild, Storybook)
- @joint/layout-directed-graph - Graph layout algorithms
- @joint/layout-msagl - Microsoft MSAGL layout integration
- @joint/shapes-general - General-purpose diagram shapes
- @joint/eslint-config - Shared ESLint configuration
Core Library Structure (/packages/joint-core/src)
The library follows an MVC pattern:
mvc/- Base MVC components: Model, View, Collection, Events, Domdia/- Diagramming API built on MVC:Graph.mjs- Graph data structure and cell managementPaper.mjs- SVG canvas and rendering engineElement.mjs/ElementView.mjs- Diagram nodesLink.mjs/LinkView.mjs- Connections between elements
g/- Geometry library (points, lines, curves, polygons, matrices)V/- Vectorizer for SVG manipulationconnectors/- Link path strategies (line, curve, bezier, jumpover)routers/- Link routing algorithms (manhattan, orthogonal, metro)anchors/- Connection point anchors on elementshighlighters/- Visual highlighting mechanismslinkTools/,elementTools/- Interactive manipulation toolsshapes/- Built-in shapes (standard)layout/- Built-in layouts (port, port label)alg/- Graph algorithms (DFS, BFS, shortest path)
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 · 122 lines · 1,220 tokens per session scan A c846690b9999
joint CLAUDE.md is an instructions file published in the GitHub repository clientIO/joint (5,366 stars, last pushed 4d ago), licensed MPL-2.0. It adds 1,220 tokens to every session, about $0.0061 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
qiankun AGENTS.md
Instructions for umijs/qiankun, covering qiankun project knowledge base, structure, architecture (big picture), commands and build (vite 8 → package javascript; tsc → declarations).
qiankun CLAUDE.md
Instructions for umijs/qiankun: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
featurevisor AGENTS.md
Instructions for featurevisor/featurevisor, covering links, stack, packages, examples and installation.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.