nimbus: Instructions file for Claude Code

CLAUDE.md

nimbus CLAUDE.md is an instructions file for Claude Code from cloudflare/nimbus. It costs 3,629 tokens per session, scanned A, original, MIT.

Repository instructions for Nimbus, a documentation-site framework built with Astro. They explain its user-editable starter files, shared plumbing package, optional registry components, deployment model, and folder layout.

In plain words
What is it for?
Use them when developing Nimbus, its starter project, the nimbus-docs package, registry additions, or Cloudflare and other static deployment setups.
Why use it?
They help contributors understand which parts belong to the user’s site, which are framework internals, and where new components or utilities should go.

Instructions file for Claude Code ✓ vendor

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is cloudflare/nimbus's own configuration. It tells Claude Code how to work on nimbus itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nimbus configures →

About the project

cloudflare/nimbus scaffolds a complete Astro documentation website as editable files in a repository, including its layouts, components, styles, routes, and content. It is for people building documentation sites that both humans and coding agents can use. The catalogue instruction helps coding agents work with Nimbus documentation projects.

cloudflare/nimbus · 1,448 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to cloudflare/nimbus. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cloudflare/nimbus/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cloudflare/nimbus

Made for: Claude Code.

Wrote 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.

agentmods badge for nimbus CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cloudflare/nimbus/claude-md/github.svg)](https://agentmods.dev/instructions/cloudflare/nimbus/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cloudflare/nimbus/claude-md"><img src="https://agentmods.dev/badge/instructions/cloudflare/nimbus/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nimbus CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cloudflare/nimbus/claude-md"><img src="https://agentmods.dev/badge/instructions/cloudflare/nimbus/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,629 This file is loaded in full into every session.
When invoked 3,629 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03629 $0.03629
Opus 5.5 $0.01452 $0.01452
Sonnet 5.5 $0.00726 $0.00726
Haiku 4.5 $0.00363 $0.00363

Measured 8d ago against content hash 4bee44e59943, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nimbus 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 8d 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.

CLAUDE.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Nimbus — agent context

Read this first if you're an AI agent picking up work on the Nimbus codebase. Sister file CLAUDE.md mirrors this content — keep them in sync.

What this project is

Nimbus builds documentation sites on Astro. The architecture splits into three tiers:

  • User-owned starter files — visible UI components, layouts, and styling. Copied into the user's repo by create-nimbus-docs and edited freely from then on.
  • nimbus-docs npm package — invisible plumbing (data helpers, validation, integration wiring, behavior primitives). Imported, not forked.
  • Registry — optional components, utilities, and agent-handoff features installed on demand via nimbus-docs add <slug>.

Cloudflare is a first-class deploy target (the scaffolder defaults to it and ships wrangler.jsonc), but the framework is deploy-target agnostic — static output runs anywhere.

Repo layout

monorepo/
├── packages/
│   ├── nimbus-docs/                       framework — integration, helpers, schemas, types, `nimbus` CLI
│   ├── nimbus-starter-source/             canonical source — fat tree; doubles as kitchen-sink dev app
│   │   ├── src/                           components, layouts, pages, demo content
│   │   ├── templates/                     per-variant content overrides (empty/, …)
│   │   └── starter.manifest.mjs           declarative generation policy (registry-only slugs, dev-only paths, variants)
│   └── create-nimbus-docs/                scaffolder (`npx @cloudflare/create-nimbus-docs`) — CLI only, no templates
│       └── scripts/copy-template.mjs      generator: canonical source + manifest → variant dirs (--out)
├── apps/
│   └── www/                               docs site + registry hosting
│       └── registry/                      manifests.ts (source), components/, features/, registry.json
├── examples/
│   └── local/                             local sandbox (not drift-mirrored)
├── scripts/
│   ├── release.mjs                        release orchestration (detect → generate → verify → sync+tag → publish)
│   ├── sync-templates-repo.mjs            sync generator output to the orphan templates branch + tag templates-v<version> (idempotent)
│   ├── templates-check.mjs                PR CI: generate + scaffold + build
│   ├── check-no-major.mjs / freshness-guard.mjs  release guards
│   ├── local.mjs / local-add.mjs          local sandbox helpers
├── .generated/                            gitignored generator output (templates); scratch for local/CI/release
├── pnpm-workspace.yaml
└── tsconfig.base.json

Read the full file on GitHub · 177 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. 8d ago Changed · +38 tokens per session 4bee44e59943
  2. 10d ago Changed 48253eb4bfba
  3. 23d ago Changed · +40 tokens per session c8f30ccf4487
  4. 1mo ago Changed · +11 tokens per session 00d180a8a80e
  5. 1mo ago First seen · 177 lines · 3,540 tokens per session scan A c2e4fd2f8bb0

Subscribe to this mod's changes

nimbus CLAUDE.md is an instructions file published in the GitHub repository cloudflare/nimbus (1,448 stars, last pushed today), licensed MIT. It adds 3,629 tokens to every session, about $0.0145 per session on Opus 5.5. 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 instructions, from other repositories

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).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens