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.
curl -O https://raw.githubusercontent.com/garfiec/Librechat-Mobile/develop/CLAUDE.mdgit clone --depth 1 https://github.com/garfiec/Librechat-MobileWrote 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/garfiec/librechat-mobile/claude-md)<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.
<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>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 5.1 | $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 |
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.
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, andAdaptive*components in:core:uiself-theme into one of two variants. Screens useAdaptive*(detekt bans raw M3 chrome) and don't branch on style. See "The pattern" incore/ui/CLAUDE.md. - Distribution channels: open source (
fossflavor,com.garfiec.librechat; XcodeRelease) vs store (playflavor,com.garfiec.librechat.play; XcodeRelease-AppStore). A behaviour that differs between them is a field onChannelPolicy(:core:common), injected where needed; a preference default that differs is aperChannel(…)default inAppPreferences(:core:data). Never branch onBuildConfig.FLAVORorDistributionChannelat a call site (detekt bans the import in non-test code;:core:commonuses it from its own package), and don't callChannelPolicy.pickfrom a feature either: add a field. A channel that can't be determined fails at launch by design. Seedocs/RELEASING.md"Distribution channels".
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.
- 3d ago Changed · +1 lines · +21 tokens per session ae7493678124
- 15d ago Changed · +1 lines · +24 tokens per session 6524670b356a
- 24d ago Changed · +9 lines · +199 tokens per session 1d5868bf514c
- 1mo ago Changed · +4 lines · +88 tokens per session db86fdd46750
- 1mo ago Changed · +1 tokens per session e2bce2c241e5
- 2mo ago First seen · 80 lines · 1,456 tokens per session scan A fdf90c79c54d
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.
Librechat-Mobile CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Librechat-Mobile CLAUDE.mdgarfiec/Librechat-Mobile | Instructions file | 146 | yesterday | Apache-2.0 | A | 1,789 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |