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/zhnd/lumo/claude-mdgit clone --depth 1 https://github.com/zhnd/lumoWrote 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/zhnd/lumo/claude-md)<a href="https://agentmods.dev/instructions/zhnd/lumo/claude-md"><img src="https://agentmods.dev/badge/instructions/zhnd/lumo/claude-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 | $0.03048 | $0.03048 |
| Opus 5 | $0.01524 | $0.01524 |
| Sonnet 5 | $0.00610 | $0.00610 |
| Haiku 4.5 | $0.00305 | $0.00305 |
Grade B, and why
lumo CLAUDE.md scanned grade B 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
3. Configures `~/.claude/settings.json` for OTLP export and hooks How it starts
The opening of the file, as written. The whole thing — 290 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.
Package Manager
This project uses pnpm exclusively. Always use pnpm / pnpm dlx instead of npm / npx.
Project Overview
Lumo is a local-first desktop application for monitoring Claude Code usage. It collects telemetry data via OpenTelemetry Protocol (OTLP) and hook events, then displays usage analytics in a native desktop UI.
Key characteristics:
- No accounts, no cloud services, no data leaves your machine
- All data stored locally in SQLite at
~/.lumo/ - Daemon auto-installed and managed by the desktop app on macOS
Components
- Daemon (
crates/daemon/): Standalone HTTP service (Axum) that receives OTLP metrics/logs and hook notifications from Claude Code - Shared Library (
crates/shared/): Common database layer (entities, repositories, migrations) used by both daemon and Tauri app - Tauri App (
src-tauri/): Desktop application shell with native OS integration, IPC commands, and business services - Frontend (
packages/ui/): React-based UI (pnpm workspace package@lumo/ui)
Module Documentation
Each module has its own CLAUDE.md with detailed patterns and guidelines:
crates/daemon/CLAUDE.md- Daemon service architecturecrates/shared/CLAUDE.md- Database layer and entity patternssrc-tauri/CLAUDE.md- Tauri backend, services, and IPC commandspackages/ui/CLAUDE.md- Frontend architecture and component patterns
Architecture
System Overview
Claude Code
|
|-- OTLP logs/metrics (HTTP JSON) --> Lumo Daemon (port 4318) --> SQLite (~/.lumo/lumo.db)
|-- Hook events (/notify endpoint) ----^ |
v
Tauri App (reads DB)
|
v
React UI (Next.js SSG)
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.
- 4d ago First seen · 290 lines · 3,048 tokens per session scan B 3c2a9c35a1bb
lumo CLAUDE.md is an instructions file published in the GitHub repository zhnd/lumo (147 stars, last pushed 4mo ago), licensed MIT. It adds 3,048 tokens to every session, about $0.0152 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.