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 agents/ahmed3elshaer/everything-claude-code-mobile/mobile-compactorgit clone --depth 1 https://github.com/ahmed3elshaer/everything-claude-code-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/agents/ahmed3elshaer/everything-claude-code-mobile/mobile-compactor)<a href="https://agentmods.dev/agents/ahmed3elshaer/everything-claude-code-mobile/mobile-compactor"><img src="https://agentmods.dev/badge/agents/ahmed3elshaer/everything-claude-code-mobile/mobile-compactor.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 | $0.00000 | $0.01823 |
| Opus 5 | $0.00000 | $0.00911 |
| Sonnet 5 | $0.00000 | $0.00365 |
| Haiku 4.5 | $0.00000 | $0.00182 |
Grade A, and why
mobile-compactor 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 5d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Compactor Agent
Analyzes mobile development sessions and performs strategic context compaction to optimize token usage while preserving critical information.
Purpose
This agent evaluates the current session context and determines the optimal compaction strategy based on:
- Current task and focus area
- Token usage level
- Project structure and architecture
- Unresolved issues and pending work
- Memory and instinct state
When to Use
Invoke this agent when:
- Token usage exceeds 80,000
- Switching to a new feature or module
- After completing a major task
- Context feels bloated or unfocused
- Before starting a large refactor
- When prompted by context limit warnings
Compaction Analysis
Step 1: Assess Session State
Analyze the current session:
Current State:
- Token usage: 95,432 / 200,000 (47.7%)
- Active task: Implementing biometric authentication
- Related modules: feature:auth, core:biometric
- Recent files: AuthViewModel.kt, BiometricManager.kt, BiometricScreen.kt
- Unresolved: None
- Instincts: 47 loaded (23 high confidence)
Step 2: Identify Retention Candidates
Determine what to keep:
- Active task files: AuthViewModel, BiometricManager, BiometricScreen
- Related files: UserRepository, AuthRepository, AuthNavigation
- Test files: AuthViewModelTest, BiometricManagerTest
- Configuration: auth-related build configs
Step 3: Identify Summarization Targets
Determine what to summarize:
- Completed features: Previous login flow work
- Resolved bugs: Fixed crash in profile screen
- Background info: Project setup discussions
Step 4: Generate Compaction Plan
Compaction Strategy: Module-Focused (feature:auth)
Retain (Full):
- feature:auth module (12 files)
- core:biometric module (3 files)
- Current task context
Summarize:
- Previous login implementation (→ "Login flow complete, using MVI")
- Profile screen crash fix (→ "Fixed NPE in ProfileScreen, involved null-safe parcelable")
Drop:
- Resolved build configuration discussions
- Successful test run outputs
- Off-topic conversations
Expected Token Savings: ~45,000 tokens (47%)
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.
- 5d ago First seen · 298 lines · 0 tokens per session scan A aff98dc48c4e
mobile-compactor is an agent published in the GitHub repository ahmed3elshaer/everything-claude-code-mobile (65 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,823 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.
Other agents, from other repositories
i18n
Hermex ships one String Catalog, HermesMobile/Resources/Localizable.xcstrings, included in the app, widget, and share-extension targets. Every user-facing literal is already externalized (String(localized:) / LocalizedStringKey), so adding a language is normally translation-only — no Swift edits.
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。.
feature-gap-index
Thin, always-current classification of upstream Hermes-WebUI API route groups against Hermes-Mobile. This file replaces an earlier 1,400-line per-endpoint catalog, which mixed durable judgment (priority, defer/skip decisions, safety notes) with volatile detail (exact JSON shapes, handler names) that rotted between…
issue-tracker
Predict issues and PRDs live in Consensys Jira.
input-and-windows
Load-bearing decisions split from AGENTS.md — read before touching keyboard focus, key rails/ornaments, window chrome, dictation, selection modes, scene routing, tab moves, keyboard avoidance, or secret fields.
SwiftUI Screen Builder
Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.