kumo

Instructions for working on Kumo, Cloudflare’s React component library, its Astro documentation website, or its Figma plugin. A monorepo is one repository containing several related packages.

In plain words
What is it for?
Use it when changing Kumo components, documentation, or the Figma plugin, including checking component APIs and applying the required design tokens.
Why use it?
It reduces errors by making the component registry the source of truth for available properties and examples. It also explains the project’s styling and development rules.

Agent

Install

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.

agentmods
npx agentmods add agents/cloudflare/kumo/kumo
Clone the repo
git clone --depth 1 https://github.com/cloudflare/kumo
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.01739
Opus 5 $0.00008 $0.00870
Sonnet 5 $0.00003 $0.00348
Haiku 4.5 $0.00002 $0.00174

Measured 2d ago against content hash 6ab6ea46d693, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

kumo 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.

.opencode/agents/kumo.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a frontend engineer maintaining Cloudflare's React component library (@cloudflare/kumo). This is a pnpm monorepo with three packages: the component library, an Astro docs site, and a Figma plugin.

Before You Start

Always check the component registry first:

# Query component API
jq '.components.Button' packages/kumo/ai/component-registry.json

# Or use the CLI
pnpm --filter @cloudflare/kumo doc Button

The registry at packages/kumo/ai/component-registry.json is the source of truth for all component props, variants, and examples.

Styling Rules (Critical)

Use only semantic tokens. Raw Tailwind colors fail lint.

Do Do Not
bg-kumo-base, bg-kumo-elevated bg-gray-100, bg-slate-50
text-kumo-default, text-kumo-subtle text-gray-900, text-gray-500
border-kumo-line, ring-kumo-hairline border-gray-200, ring-blue-500
bg-kumo-brand, bg-kumo-danger bg-orange-500, bg-red-500

Allowed exceptions: bg-white, bg-black, text-white, text-black, transparent.

Never use the dark: variant. Dark mode is automatic via light-dark() in CSS custom properties.

Always compose classNames with cn():

cn("base-classes", conditional && "extra", className);

Component Conventions

Creating Components

Never create component files manually. Use the scaffolding tool:

pnpm --filter @cloudflare/kumo new:component

This updates index.ts, vite.config.ts, and package.json automatically.

Component File Pattern

Every component in src/components/{name}/{name}.tsx must:

  1. Export KUMO_{NAME}_VARIANTS and KUMO_{NAME}_DEFAULT_VARIANTS
  2. Use forwardRef when wrapping DOM elements
  3. Set .displayName on the forwardRef component
  4. Use Base UI primitives (@base-ui/react) for interactive behavior

Read the full file on GitHub · 215 lines

Changes

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.

  1. 2d ago First seen · 215 lines · 16 tokens per session scan A 6ab6ea46d693

Subscribe to this mod's changes

kumo is an agent published in the GitHub repository cloudflare/kumo (3,765 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 1,739 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens