lumen: Instructions file for Claude Code

CLAUDE.md

lumen CLAUDE.md is an instructions file for Claude Code from Sardor-M/lumen. It costs 1,272 tokens per session, scanned A, original, MIT.

Repository instructions for Lumen, a local-first tool that turns articles, papers, and videos into searchable notes and a knowledge graph. A monorepo is one repository containing several related applications, which Lumen uses for its command-line tool, website, and browser extension.

In plain words
What is it for?
Use them to develop, build, lint, test, format, or run Lumen and one of its individual applications with pnpm and Turborepo.
Why use it?
They explain the project layout, required coding rules, and commands for working across its applications.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Sardor-M/lumen's own configuration. It tells Claude Code how to work on lumen 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 lumen configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Sardor-M/lumen. 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/Sardor-M/lumen/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Sardor-M/lumen

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 lumen CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sardor-m/lumen/claude-md.svg)](https://agentmods.dev/instructions/sardor-m/lumen/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sardor-m/lumen/claude-md"><img src="https://agentmods.dev/badge/instructions/sardor-m/lumen/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,272 This file is loaded in full into every session.
When invoked 1,272 The same file — it is already loaded in full.
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 5.1 $0.01272 $0.01272
Opus 5 $0.00636 $0.00636
Sonnet 5 $0.00254 $0.00254
Haiku 4.5 $0.00127 $0.00127

Measured 6d ago against content hash 9f29dc289d19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

lumen 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 6d 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lumen — Project Rules

What is Lumen

Local-first knowledge compiler. Ingest articles/papers/videos → chunk → store in SQLite → search via BM25 → compile into knowledge graph via LLM.

Repo structure

Monorepo with Turborepo + pnpm workspaces.

lumen/
├── apps/
│   ├── cli/         — The CLI and MCP server (the engine)
│   ├── web/         — Next.js 15 web UI with Better Auth + Zod
│   └── extension/   — Browser extension (placeholder)
├── docs/            — PRODUCT-ROADMAP.md, etc.
├── turbo.json
├── pnpm-workspace.yaml
└── package.json

Commands (run from repo root)

pnpm dev                          # turbo dev — runs all apps in parallel
pnpm build                        # turbo build — builds all apps
pnpm lint                         # turbo lint
pnpm test                         # turbo test
pnpm format                       # prettier on all apps
pnpm --filter lumen-kb dev        # CLI only
pnpm --filter @lumen/web dev      # web only
pnpm --filter @lumen/web build    # web build

Hard Rules (apply to all apps)

  • type not interface. Always. No exceptions.
  • **/** JSDoc \*/not//**. Every comment is JSDoc style.
  • .js extensions in all relative imports (in apps/cli/). ESM requires it.
  • import type for type-only imports.
  • No classes. Plain functions and types only.
  • No default exports — EXCEPT in apps/web/ for Next.js framework files (page.tsx, layout.tsx, error.tsx, loading.tsx, not-found.tsx, route.ts, next.config.ts). Everywhere else uses named exports.
  • No enums. Use union types: type Foo = 'a' | 'b' | 'c'
  • No any. Use unknown or specific types.
  • Prefix unused params with _.

App-specific rules

apps/cli/

  • No console.log in commands. Use log.info/success/warn/error/heading/table/dim.
  • No process.exit(). Set process.exitCode = 1 instead.
  • .js extensions in all relative imports.

apps/web/

  • Default exports allowed for Next.js framework files only (see list above). All library code (src/lib/*, src/components/*) uses named exports.
  • Server components by default. Add 'use client' only when you need interactivity.
  • Zod for input validation — all form inputs and API route bodies go through a Zod schema in src/lib/schemas.ts.
  • Better Auth session check via auth.api.getSession({ headers: await headers() }) in server components. Redirect unauthenticated users from protected routes.
  • No .js extension in relative imports — Next.js handles it.
  • Inline export function for all UI components. Never use bottom export { ... } blocks. Write export function Button(...) not function Button(...) ... export { Button }.
  • export const for CVA variants — write export const buttonVariants = cva(...) inline.
  • shadcn base-ui uses render prop, NOT asChild. To render a component as a Link: <SidebarMenuButton render={<Link href="..." />}>. Do NOT use asChild — it leaks to DOM elements.
  • cn() from @/lib/utils for all className merging.

Read the full file on GitHub · 103 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. 6d ago First seen · 103 lines · 1,272 tokens per session scan A 9f29dc289d19

Subscribe to this mod's changes

lumen CLAUDE.md is an instructions file published in the GitHub repository Sardor-M/lumen (11 stars, last pushed 2mo ago), licensed MIT. It adds 1,272 tokens to every session, about $0.0064 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 2026-08-31.

Related

Other instructions, from other repositories

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 · 7,296 tokens

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.

openai/codex · 5,182 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens