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/cbagajurel/luno/claude-mdgit clone --depth 1 https://github.com/cbagajurel/lunoWrote 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/cbagajurel/luno/claude-md)<a href="https://agentmods.dev/instructions/cbagajurel/luno/claude-md"><img src="https://agentmods.dev/badge/instructions/cbagajurel/luno/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 | $0.03029 | $0.03029 |
| Opus 5 | $0.01515 | $0.01515 |
| Sonnet 5 | $0.00606 | $0.00606 |
| Haiku 4.5 | $0.00303 | $0.00303 |
Grade A, and why
luno 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 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.
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 — 199 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
This repo is the Android app for Luno, a self-hosted SMS gateway agent. An Android phone runs a long-lived background service that sends/receives SMS and reports device health (SIM, signal, battery, delivery status) to a backend over WebSocket (REST as fallback) — any server that speaks the Luno protocol; the backend's tech stack is out of scope for this repo. Flutter is the dashboard UI only — it never talks to telephony APIs directly.
Scope decision: Android only, for now. Linux/Windows "nodes" would require external USB GSM modems and AT-command integration (no shared code with the Android telephony layer); macOS has no cellular hardware path at all. Both are explicitly out of scope until the Android app is solid. Don't add Linux/Windows/macOS platform code or dependencies without being asked.
The backend and dashboard are separate concerns (separate repositories), not part of this codebase. The node is backend-agnostic: it prescribes no server technology (Firebase, Supabase, Express, Next, Nest, … all work equally), it hardcodes no endpoints (they're runtime config set at pairing), and it depends only on the versioned wire protocol. How the backend is built is not our concern — the node's job is: receive a command, act on the radio, report what happened.
State of the repo
Progress: M1–M17 complete, plus the pairing-session system (2026-07-19).
docs/milestones.md covered the initial build-out (M1–M18)
and is kept for history; work is no longer gated on its running order.
Pairing sessions (2026-07-19). The node is now a pure pairing client: it
submits a code — typed or scanned — and renders the backend's verdict, enforcing
no expiry, usage limit, revocation or approval rule of its own, so every
enrolment policy is backend config rather than an app release. New/changed:
backend/auth/{PairingPayload,PendingEnrollment,SealedValueStore,InstallId}.kt,
a policy-driven PairingError taxonomy with forward-compatible unknown codes,
RestClient enroll v2 (nonce, installId, sessionId, reserved publicKey,
status: approved|pending|denied) plus POST /enroll/status, and QR pairing
(versioned luno://pair / JSON payload parsed natively; mobile_scanner is a
viewfinder only). See docs/pairing.md — that file is the
contract the @luno-oss/* server SDKs implement.
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 · 199 lines · 3,029 tokens per session scan A 794df0abe5fc
luno CLAUDE.md is an instructions file published in the GitHub repository cbagajurel/luno (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,029 tokens to every session, about $0.0151 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.
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.