An agent specification for an Android marketplace where people can browse, search, filter, view, create, edit, and start chats with other agents.

Use it when building or extending an agent marketplace in a Kotlin mobile app, including detail pages, editor screens, server-side search, and loading more results.

It provides the screens, navigation routes, pagination, search behavior, category filters, and refresh logic needed for this feature.

CLAUDE — Agent for Claude Code by garfiec: An agent specification for an Android marketplace where people…

Install

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.

agentmods

npx agentmods add agents/garfiec/librechat-mobile/claude

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/garfiec/librechat-mobile/claude.svg)](https://agentmods.dev/agents/garfiec/librechat-mobile/claude)

Your own site

<a href="https://agentmods.dev/agents/garfiec/librechat-mobile/claude"><img src="https://agentmods.dev/badge/agents/garfiec/librechat-mobile/claude.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,428 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.01428
Opus 5	$0.00000	$0.00714
Sonnet 5	$0.00000	$0.00286
Haiku 4.5	$0.00000	$0.00143

Measured 6d ago against content hash 72bf3a42edc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

CLAUDE 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.

feature/agents/CLAUDE.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

feature:agents

Screens

AgentMarketplaceScreen -- grid of agent cards with search and category filters
AgentDetailScreen -- full agent info with "Start Chat" action

Sealed interface: AgentsRoute : NavKey with typed route classes
Routes: AgentMarketplace (grid), AgentDetail(agentId: String) (detail), AgentEditorCreate, AgentEditorEdit(agentId: String) (all @Serializable)
Feature entries registered via EntryProviderScope<NavKey>.agentsEntries()
onStartChat(agentId) callback navigates to chat with the selected agent

Marketplace ViewModel

AgentMarketplaceViewModel uses server-side pagination via AgentRepository.getAgentsPaginated()
Page size: 10 agents per page
Categories fetched from getAgentCategories() API (server-driven, not client-derived)
onCategorySelected() toggles category filter and resets to page 1
onSearchQueryChanged() debounces 500ms, then resets to page 1 with server-side search
loadMore() appends next page; no-ops if already loading or no more pages
Pull-to-refresh resets to page 1
Gotcha: Search and category changes reset pagination — always load from page 1 when filters change

Agent Card Layout

Card: 136dp height, endpoint avatar + name (2-line clamp) + description (2-line clamp) + "By {author}"
Category badge at top-right corner
Tap opens agent detail

Agent Detail

AgentDetailViewModel loads single agent by ID
Shows: large avatar, name, description, capabilities/tools list
Actions: Pin/Unpin, Copy link, "Start Chat" button
"Start Chat" flow: sets endpoint: "agents" + agent_id, creates conversation template, navigates to new chat

Data Layer

AgentRepository in :core:data wraps AgentsApi from :core:network
API: GET /api/agents (list), GET /api/agents/:id (detail), GET /api/agents/categories
Categories are server-driven, not hardcoded; special values: "promoted" (Top Picks), "all"

Infinite Scroll

LazyVerticalGrid with rememberLazyGridState() + derivedStateOf for scroll detection
Triggers loadMore() when last visible item is within 3 of the end
Shows CircularProgressIndicator in a full-span grid item while loading more

Read the full file on GitHub · 89 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.

6d ago First seen · 89 lines · 0 tokens per session scan A 72bf3a42edc5

Subscribe to this mod's changes

CLAUDE is an agent published in the GitHub repository garfiec/Librechat-Mobile (85 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,428 tokens. 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.

Building agents Mobile ai-assistant ai-chat android anthropic chat-bot chatgpt

e2e-verifier

FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.

K9i-0/ccpocket · 65 tokens

crash-investigator

Investigates a Firebase Crashlytics issue end-to-end for Meshtastic-Android and returns a tight, distilled verdict. Pulls the issue + events via the Firebase MCP, maps the affected versionCode(s) to git tag/commit/Play track, locates the suspect code from the stack frames, and reports root-cause hypothesis + fix area…

meshtastic/Meshtastic-Android · 117 tokens

CLAUDE