Librechat-Mobile: Instructions file for Claude Code

CLAUDE.md

Librechat-Mobile CLAUDE.md is an instructions file for Claude Code from garfiec/Librechat-Mobile. It costs 1,789 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a native Android and iOS client for LibreChat. They explain the technology choices, module layout, and rules for adding feature modules.

In plain words
What is it for?
Use them when working on authentication, networking, local storage, navigation, shared Kotlin code, Android screens, or iOS integration.
Why use it?
They give coding agents the structure needed to change the mobile app without placing code in the wrong layer or breaking its shared architecture.

Instructions file for Claude Code

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

This is garfiec/Librechat-Mobile's own configuration. It tells Claude Code how to work on Librechat-Mobile 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 Librechat-Mobile configures →

Reuse

Borrowing it

Nothing to install: this file belongs to garfiec/Librechat-Mobile. 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/garfiec/Librechat-Mobile/develop/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/garfiec/Librechat-Mobile

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 Librechat-Mobile CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/garfiec/librechat-mobile/claude-md/github.svg)](https://agentmods.dev/instructions/garfiec/librechat-mobile/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/garfiec/librechat-mobile/claude-md"><img src="https://agentmods.dev/badge/instructions/garfiec/librechat-mobile/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 Librechat-Mobile CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/garfiec/librechat-mobile/claude-md"><img src="https://agentmods.dev/badge/instructions/garfiec/librechat-mobile/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,789 This file is loaded in full into every session.
When invoked 1,789 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 $0.01789 $0.01789
Opus 5.5 $0.00716 $0.00716
Sonnet 5.5 $0.00358 $0.00358
Haiku 4.5 $0.00179 $0.00179

Measured 3d ago against content hash ae7493678124, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Librechat-Mobile 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 3d 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Switchboard

Native mobile client for LibreChat (Android & iOS). Connects to existing LibreChat backend servers (no backend changes). Users specify server URL during onboarding.

Tech Stack

  • UI: Jetpack Compose + Navigation Compose 3 (Nav 3)
  • DI: Koin (KMP-ready)
  • Network: Ktor Client (OkHttp engine)
  • Serialization: Kotlinx Serialization
  • Local Storage: Room (cache), DataStore (prefs), EncryptedSharedPreferences (tokens)
  • Build: Gradle 9.5.1, AGP 9.2.1, Kotlin 2.4.10, compileSdk 37, minSdk 26

Module Layout

app/                  → Single Activity, adaptive navigation (phone/tablet)
shared/               → KMP shared framework (iOS entry point, shared navigation)
build-logic/          → 13 convention plugins for consistent Gradle config
core/common/          → Result type, dispatcher DI, coroutine scopes, extensions
core/model/           → @Serializable data classes (pure Kotlin, no Android deps)
core/network/         → Ktor client, 16 API services, SSE client, auth interceptor
core/data/            → Room DB, DataStore, EncryptedSharedPrefs, repository impls
core/ui/              → Material 3 theme, shared composables
feature/auth/         → Server URL, Login, Register, 2FA, OAuth, Forgot Password
feature/chat/         → Real-time chat with SSE streaming, message rendering
feature/conversations/→ Paginated list, CRUD, tags, search, export/import
feature/settings/     → Account, appearance, about, danger zone
feature/agents/       → Agent marketplace with search and categories
feature/files/        → File upload, management, image viewer
testing/speech-fixture/ → Stand-in speech provider APK for scripts/verify-speech-services.py (never ships)

Each module has its own CLAUDE.md with specific guidance.

Architecture Rules

  • Feature modules depend on :core:* only, never on each other
  • Single Activity with Nav 3 (NavDisplay + NavBackStack<NavKey> + entryProvider)
  • Unidirectional data flow: UI → ViewModel → Repository → API/Room
  • Room is a read-through cache; server is source of truth
  • Custom SSE parser over raw ByteReadChannel (not Ktor SSE plugin)
  • UI is style-agnostic: the user's Material / Liquid Glass choice flows down as a CompositionLocal from LibreChatTheme, and Adaptive* components in :core:ui self-theme into one of two variants. Screens use Adaptive* (detekt bans raw M3 chrome) and don't branch on style. See "The pattern" in core/ui/CLAUDE.md.
  • Distribution channels: open source (foss flavor, com.garfiec.librechat; Xcode Release) vs store (play flavor, com.garfiec.librechat.play; Xcode Release-AppStore). A behaviour that differs between them is a field on ChannelPolicy (:core:common), injected where needed; a preference default that differs is a perChannel(…) default in AppPreferences (:core:data). Never branch on BuildConfig.FLAVOR or DistributionChannel at a call site (detekt bans the import in non-test code; :core:common uses it from its own package), and don't call ChannelPolicy.pick from a feature either: add a field. A channel that can't be determined fails at launch by design. See docs/RELEASING.md "Distribution channels".

Read the full file on GitHub · 95 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. 3d ago Changed · +1 lines · +21 tokens per session ae7493678124
  2. 15d ago Changed · +1 lines · +24 tokens per session 6524670b356a
  3. 24d ago Changed · +9 lines · +199 tokens per session 1d5868bf514c
  4. 1mo ago Changed · +4 lines · +88 tokens per session db86fdd46750
  5. 1mo ago Changed · +1 tokens per session e2bce2c241e5
  6. 2mo ago First seen · 80 lines · 1,456 tokens per session scan A fdf90c79c54d

Subscribe to this mod's changes

Librechat-Mobile CLAUDE.md is an instructions file published in the GitHub repository garfiec/Librechat-Mobile (146 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,789 tokens to every session, about $0.0072 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

Librechat-Mobile CLAUDE.md compared with instructions from other repositories

Librechat-Mobile CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Librechat-Mobile CLAUDE.mdgarfiec/Librechat-MobileInstructions file146yesterdayApache-2.0A1,789Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode